Suggest relevant skills from local SKILL.md files based on a prompt, enforcing a token budget to return the top matches.
Lexically rank skills for a prompt. Hard cap 3; default token budget 4000 (CJK-aware). Returns reasons and dropped (cap/budget).
| Name | Required | Description | Default |
|---|---|---|---|
| budget | No | Token budget (default 4000); never raises the max-3 cap | |
| prompt | Yes | User or agent task prompt |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the burden of disclosing behavior. It says the tool 'Returns reasons and dropped (cap/budget)' and uses the verb 'suggest,' which implies a read-only ranking operation, but it never explicitly states that it has no side effects or does not modify skills.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, compact sentence that conveys the core behavior, constraints, and return highlights without unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description mentions that returns include 'reasons and dropped (cap/budget),' but it does not fully specify the result shape or how the ranked skills are represented. This is adequate for a simple tool but leaves some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes both parameters, including the default budget and the cap constraint. The description adds 'CJK-aware' and repeats the hard cap, but it does not substantially deepen parameter understanding beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Lexically rank skills for a prompt.' This uses a specific verb and object, and is distinct from sibling tools like list_skills or bind_skills.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides constraints like 'Hard cap 3' and a default token budget, but does not explain when to use this tool versus alternatives such as list_skills, bind_skills, or estimate_tokens. There is no explicit when-to-use or when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.