search_docs

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

No annotations are present, so the description carries the burden, and it discloses the critical behavioral trait: the default search is scoped to the skill layer only and misses per-class API reference and DEFAULTS content. It also implies a ranked-sections return shape. It stops short of describing result structure or limits in detail, but for a read-only search the key caveat is covered.

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?

Two sentences, front-loaded with purpose before the caveat, with no filler content. The NOTE sentence is dense with sibling names and examples (cornerRadius, strokeDasharray) that slightly outweigh what an agent needs to decide whether to call the tool.

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 explains what is returned ('matching sections ranked by relevance') and covers the main behavioral gap (skill-only default scope). It is nearly complete for a 3-parameter search tool, missing only finer return details such as result fields or truncation behavior.

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 100% and both scope and maxResults already carry descriptions, so the baseline is 3. The description reinforces the meaning of the scope default (what extended docs contain and why they matter), which is useful context but not syntax or format 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?

States a specific verb and resource ('Search the curated amCharts 5 skill docs (SKILL.md + chart references) for a keyword or topic') and adds the return semantics ('matching sections ranked by relevance'). The NOTE distinguishes it from sibling tools such as search_all, get_api_reference and get_doc by naming exactly where each reaches.

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?

Explicitly states the default behavior ('by default this scans ONLY the skill layer'), the condition under which the default is insufficient, and the concrete alternatives to select instead (pass scope:'all', or use search_all / get_api_reference / get_doc).

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