bitHuman docs

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

Annotations already declare readOnly/idempotent/no destructive behavior, and the description adds genuine context beyond them: the exact return payload shape ({id, title, text, url, metadata}), that it is a JSON response, the refusal conditions (unknown path, non-bithuman URL), and that no sign-in is required. Only pagination/size limits are unaddressed.

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-loads what is fetched and how it is identified, then packs return shape, example, error cases, and auth status into a compact paragraph. Dense but every sentence carries distinct information.

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 present, the description compensates by naming the returned fields, and it also covers error behavior and auth. Nothing an agent needs to invoke 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 100%, so the baseline is 3, but the description goes further by stating where the id originates (`search`) and giving a concrete example call ({"id": "/api/agents"}) that clarifies expected formatting.

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 (fetch) and resource (a docs page as markdown) and immediately distinguishes itself from the sibling `search` by noting the id comes from a prior search. An agent can pick this tool over search without opening the 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?

Clearly ties usage to the `search` tool for obtaining the id and explains both accepted identifier forms. It lacks an explicit 'do not use this when...' clause, but the routing context is unambiguous.

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

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description goes further with return ordering, default and max result counts, the fact that `text` is only a short snippet, and the error/empty-result semantics — all beyond what annotations provide. It stops short of auth or rate-limit context, so not a full 5.

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 purpose, then return shape, then a concrete example, then edge-case behavior, then the OpenAPI link. Dense but every sentence carries distinct information with no filler or repetition.

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?

There is no output schema, so the description correctly compensates by spelling out the JSON return shape ({results: [{id, title, url, section, text}]}) and ordering. Error and empty-result behavior plus the search-to-fetch path make the definition self-sufficient for correct invocation.

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 100%, so baseline is 3 and the schema already documents limit, query, and section. The description adds value with a concrete worked example combining `query` and `section`, plus the actionable tip to drop `section` on no-match, which clarifies the section filter's role beyond the enum list.

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 opens with a specific verb+resource ('Search docs.bithuman.ai') and enumerates the content covered (avatar SDKs, REST API, deployment, models, pricing). It explicitly distinguishes itself from the sibling by noting that `fetch` is what you use for the whole page once you have an `id`.

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 states when the tool works and how to recover from failure: empty query is an error, no match returns an empty list and you should try fewer/other words or drop `section`. It also routes the agent to `fetch` as the follow-up for full page content, giving a clear search-then-fetch workflow.

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