mcp-tool-selection-evaluator SKILL.md skillA
mcp-tool-selection-evaluator from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pramoddutta/aitesterblueprint4x/mcp-tool-selection-evaluator@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pramoddutta/aitesterblueprint4x
- Path
chapter_14_MCP_Create_VIBE/testskill-finder-mcp/skills/framework-packs/mcp-pack/mcp-tool-selection-evaluator/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Oct 10, 2026
- Size
- 4,460 bytes
- Repository stars
- 14
- License
- none declared
Builds a golden question set and scoring harness that checks whether an LLM picks the right MCP tool with the right arguments, and reports tool-selection accuracy. Use when an engineer says "is the model calling the right tool", "evaluate tool selection for my MCP server", "build a golden set for these tools", or shares tools/list output with bad transcripts. Produces golden cases, a scorer, and an accuracy report draft the engineer runs against the real model.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# MCP Tool Selection Evaluator You measure **whether the model chooses the right tool, with the right arguments, for real user questions**, and turn every miss into a concrete fix to a tool name, schema, or description. ## When to use - Tools were added or renamed and you need to know if selection got better or worse. - Users report the agent calls `search` when it should call `get`, or invents arguments. - You want a release gate for an MCP server that is consumed by an LLM. ## Workflow 1. **Freeze the tool surface.** Capture `tools/list` (Inspector CLI or `client.list_tools()`) and store a hash of names, descriptions, and schemas; evaluate exactly what the model sees. 2. **Write golden cases.** Per tool: 3-5 asks and paraphrases, argument extraction (IDs, enums, numbers), confusable pairs (search vs get), multi-step asks (expect the first call), and negatives where no tool fits. Fields: `question`, `expected_tool` (or null), `expected_args`. 3. **Get labels reviewed.** Domain owners confirm expected tools; mark ambiguous questions and ask instead of forcing a label. Start with 30-50 cases and keep a held-out slice. …
Read the whole file at its exact version.
How to install
mdr add pramoddutta/aitesterblueprint4x/mcp-tool-selection-evaluator@sha256:0113bd3ab951b0a5The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ltxotogqdwagadwj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 10, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4460 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ltxotogqdwagadwj GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/mcp-tool-selection-evaluator GET https://markdownregistry.com/api/v1/blob/0113bd3ab951b0a5a384790380b30a8123e87e05199bd252502b7ebb3ec71200
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.