get_docs

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

With no annotations, the description carries the full burden and discharges it: version fallback semantics, curated-vs-resolved matching, Source-line composition, "Source: none" for uncached content, budget-refusal behavior, and an explicit prompt-injection stance (fetched text is fenced and labelled as data). This is well beyond what any annotation could convey.

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 with purpose then usage before the dense behavioral detail, and nearly every clause carries operational value. It is packed tight—the trailing source-fencing and forged-instruction sentences are verbose—but nothing is filler relative to the tool's 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?

For a 5-parameter tool with no annotations and no output schema, the description covers the shape of returns (document head and section list, snippets with heading/context), fallback and failure modes, and provenance rules. Nothing an agent needs to call it correctly is missing.

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 coverage is already 100%, so the baseline is 3; the description still adds meaning not in the schema, notably that topic ranks matching sections and that unknown library names resolve through npm/PyPI metadata to docs or a GitHub README, distinguishing nonexistent packages from unreachable docs. The mode/version parameters are largely restated rather than extended, which keeps it short of a 5.

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?

"Get official documentation for a library" names a specific verb and resource, and the second sentence immediately distinguishes it from the sibling tool search by stating when search is the right entry point instead. An agent can tell this apart from list_libraries/search/resolve_library without opening any schema.

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?

Explicit routing: use search first when the covering library is unknown; use topic to rank sections or follow llms.txt links; use mode "snippets" for code; omit topic to get the head and section list. Alternative and when-not conditions are named rather than implied.

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