Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds valuable context: it explicitly states ranking is deterministic (aligning with openWorldHint=false), discloses that skills with safety 'warning' or missing sources are excluded, and that the result reports how many were excluded. This goes beyond the annotation's safety profile and gives the agent concrete expectations about output composition.

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, well-structured paragraph that front-loads the core purpose and input types before explaining output format and ranking behavior. Every sentence carries information—no filler. It is concise yet comprehensive for a tool of this complexity.

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 fully explains the return shape: a ranked shortlist with each entry containing the skill record and a `why` string that breaks down match reasons (matched terms, agent fit, freshness, quality, safety). It also covers exclusions and the deterministic ranking. For a 6-parameter tool with no output schema, this is unusually complete—an agent knows exactly what to expect.

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?

Schema description coverage is 83%, so the schema already documents each parameter with examples. The description adds marginal value by mapping 'languages, frameworks or dependencies' to the input concept and noting that 'skills made for it rank higher' for the agent parameter. This is helpful but does not significantly alter parameter meaning beyond what the schema provides.

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 states a specific verb ('recommend') and resource ('skills for a project'), and immediately distinguishes it from siblings like get_skill, install_skill, and search_skills by describing the ranked-shortlist output with a `why` explanation. This is clearly a recommendation tool, not a fetch, install, or generic search tool.

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?

The description implies usage: when you have a project description (task, agent, languages, etc.) and need a ranked shortlist. However, it does not explicitly state when to use this tool over alternatives like search_skills, nor does it provide exclusions (e.g., 'use search_skills when you need keyword search only'). The context is clear but lacks explicit routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.