cambrian_docs

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

No annotations are provided, so the description carries the behavioral disclosure burden. It discloses meaningful behavior: the detail default is schema, response mode also includes the request schema, full is only for examples/prose, and every endpoint detail includes the OpenAPI request schema. This goes well beyond a bare 'Get documentation' statement, though it does not mention authentication, rate limits, or error behavior.

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 dense and front-loaded with the primary purpose, then provides examples and usage rules. Every sentence adds operational detail, though a small amount of redundancy exists around the OpenAPI request schema being included in all endpoint details. Still, the length is justified by the need to disambiguate four modes of use.

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 documentation-retrieval tool with 5 optional parameters and no output schema, the description covers all necessary decision points: path formats, chain scoping, guide slugs, EVM path mapping, detail levels, mutual exclusion, fallback query behavior, and the directory result when omitted. An agent can confidently determine what to send and what to expect.

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?

Although schema coverage is 100%, the description adds significant value beyond the schema: it gives concrete path examples, explains the mutual exclusivity of path/tool_name/query, clarifies the detail enum behavior, and explains the directory output when all parameters are omitted. This compensates richly beyond the plain property descriptions.

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 states a specific verb and resource: 'Get Cambrian API documentation from docs.cambrian.org/llms.txt.' It clearly positions this as the documentation-discovery tool distinct from the many data endpoint siblings, and it enumerates exact usages such as path, tool_name, query, or the omitted directory listing.

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 description provides rich when-to-use guidance: use tool_name when the exact MCP endpoint tool is known, use query when both path and tool name are unknown, use guides/<slug> for guides, and omit all three for a directory. It also explicitly says 'Send only one of path, tool_name, or query,' which prevents invalid combinations.

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