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

With no annotations, the description carries the full burden of behavioral disclosure. It does not indicate that the tool is a read-only search, what kind of results it returns, whether it returns snippets or links, or any limitations. The only behavioral hint is that the query can be free text or code.

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 very short and scannable, with no filler. The first phrase introduces the domain, and the second gives the key input clue. It is concise, though the brevity comes at the cost of clarity.

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 tool with no output schema, no annotations, and an undocumented parameter, the description is too incomplete. It does not explain what results the agent should expect, how the docs are scoped, or how this search differs from docs_get and other sibling searches. The agent would likely need to invoke it speculatively to learn its 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?

The schema provides zero description for the single 'q' parameter, and the description only adds 'Free text or code.' This gives a general sense that q accepts natural language or code, but it does not explain format, examples, optionality, or any constraints. With 0% schema coverage, the description should compensate much more.

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 reads as a tagline ('Docs — what it is, what you get, what you pay') rather than a statement of what the tool does. It never explicitly says 'search' or 'retrieve', and it does not distinguish docs_search from the sibling docs_get. The resource is named, but the action is only implied by the tool name.

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?

There is no guidance on when to use this tool versus alternatives. The sibling set includes many search tools and docs_get, but the description does not mention any of them or give conditions for choosing this one. 'Free text or code' only hints at input format, not usage context.

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