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

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false; the description adds substantial value beyond them with 'Safe to call. Deterministic. Touches no third party. Nothing is fetched to build it: every fact comes from the headers on your own request or from a file this host already publishes.' This discloses side-effect guarantees and data provenance that the annotations do not express. There is no contradiction with the annotations.

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 long and redundant: the output contents are spelled out in the main prose and then restated almost verbatim in the closing 'Example' sentence, and it opens with a JSON-RPC POST block rather than the tool's purpose. The sibling/path enumeration is verbose and internally inconsistent ('its five siblings' followed by six listed entries, two of them named whoami). Substantial trimming and front-loading of the purpose would improve it.

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?

Given an output schema, zero parameters, and rich annotations, the description is more than sufficient for an agent to invoke the tool correctly: it covers the endpoint, empty arguments, return contents, safety, determinism, and data provenance. The only shortcoming is the confusing sibling inventory, where the stated count of five mismatches the six listed entries and two entries carry the name whoami. Nothing needed to call whoami itself 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?

With zero parameters and 100% schema coverage (empty properties, no required fields), the baseline is 4. The description reinforces this with 'Takes no arguments' and an arguments={} example, which is consistent with the schema but adds little new meaning. Given the schema already fully documents the empty parameter set, no further compensation is needed.

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, concrete purpose: it returns the caller's user-agent, the class the host books it as, whether it has been seen before, and uniquely, which robots.txt group matches that user-agent, the deciding line, and whether the current paths are allowed per RFC 9309. It also explicitly differentiates from its siblings by calling out 'the part only this server can answer.' This is a specific verb+resource description with clear sibling differentiation.

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 gives clear context for when this tool applies: 'Takes no arguments,' 'Only this server answers the last part,' and it names alternatives ('its five siblings answer one other question each about you, same empty arguments') and check_path_allowed as the equivalent RFC 9309 engine. What it lacks is a crisp decision rule for choosing whoami over each specific sibling, so the guidance is contextual rather than fully prescriptive.

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