skill_list

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

Goes well beyond the annotations by disclosing the key non-obvious behavior: listing deliberately never touches view_count, last_viewed_at or stale state, and it explains the rationale (loops would otherwise make everything look recently consulted). Annotations only say readOnlyHint=false / destructiveHint=false; the description supplies the actual side-effect semantics. Slight tension with readOnlyHint=false is explainable as conservative annotation, not a direct contradiction.

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?

Front-loaded verb and format template, followed by a short rationale paragraph; every sentence earns its place by explaining the non-consultation contract. The multi-line format block is dense but directly useful for parsing output.

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?

For a zero-required-param list tool this covers the essential semantics; an output schema exists, so repeating the format is slightly redundant but harmless. The only substantive omission is the meaning of include_archived and whether archived skills appear by default.

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 0% and the single parameter include_archived is never mentioned in the description. The output format lists a state=<active|stale|archived> field, which is ambiguous against an include_archived default of false — the agent gets no help resolving whether archived skills are omitted from the listing. This is a real gap the description could have closed in one clause.

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?

States a specific verb+resource ('List skills with telemetry') and pins down the exact per-skill fields returned (tier, origin, state, uses, views, patches, wrong, pinned, last_active). An agent can distinguish it from mutating siblings like skill_record, skill_validate and skill_manage. It stops short of naming those siblings explicitly, so differentiation is inferential rather than stated.

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 'Listing is not consultation' passage implies when this tool is wrong (when you want to register a consultation), and the note about autonomous loops listing every pass gives usage context. But no alternative tool is named and there is no explicit when-to-use prerequisite, so the guidance is implied rather than actionable.

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