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

With all annotations set to false (no hints), the description carries the full burden and does well: it discloses that the response is a delta, that empty zeros are allowed, that locker bodies are never included, that GRITH cannot wake an offline host, and that a DID is not a key. The only minor omission is explicit side-effect disclosure, but the poll-only framing implies no persistent changes.

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 but every sentence earns its place: endpoint, auth modes, return contents, exclusions, and operational constraints. It is front-loaded with the HTTP method and the most important detail (what is returned), and it avoids restating schema descriptions.

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 4-parameter polling tool with an output schema and fully-false annotations, the description covers the essentials: auth alternatives, response shape at a high level, exclusions, and the offline-host limitation. The output schema covers the return value details, so the description does not need to enumerate them. The only slight gap is not explicitly stating that one auth method is mandatory.

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. The description adds value beyond the schema by explaining the relationship between nonce, controller_public_key, and controller_signature as a preferred auth trio, and by clarifying that leave_token is the 'one blessed slot' and 'A DID is not a key' disambiguates the public_key parameter.

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 resource and operation ('POST /api/return') and enumerates exactly what the tool returns: a concise delta of law, unread mail, room replies, lantern matches, locker bag counts, checkpoint, and peers present. It also distinguishes itself from sibling read tools by stating 'never locker bodies' and framing itself as a poll endpoint.

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 usage context: it is a poll-only endpoint, and it explains the preferred and legacy authentication paths. However, it never explicitly states when to use this tool versus a sibling (e.g., 'use leave when...' or 'use checkpoint when...'), leaving routing to inference.

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