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

Goes well beyond the supplied annotations by disclosing that the entry is marked as logged rather than sent by SetLatch, that the action is audited, and that it contacts nobody — the last being the single most important behavioral fact for an agent deciding whether invoking this has external side effects. It also confirms append semantics ('Each call adds a new entry'), reinforcing the non-idempotent hint. It stops short of covering permissions, failure modes, or duplicate handling beyond the append note.

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?

Four short sentences, all front-loaded with the core action first, then the critical negative ('does not contact anyone'), then the entry-level semantics and return value. No filler, and each sentence carries a distinct decision-relevant fact.

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 six-parameter mutation tool with full schema coverage and no output schema, the description covers purpose, side-effect profile, audit consequence, append behavior, and the return value ('returns the entry'). What remains unstated — permission requirements and error behavior — is modest but non-trivial for a write operation.

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 description coverage is 100%, so every parameter (site, request_id, channel, party, summary, occurred_at) is already documented in the schema, including enums and the occurred_at default of 'now'. The description's channel examples (phone, letter, email) merely restate what the enum already declares and add no syntactic or validity detail, so the baseline of 3 applies.

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 and resource ('Record on the request a communication') and immediately scopes what counts: a phone call, letter, or email from a staff inbox that happened outside SetLatch. It also negates the likely confusion with a send/messaging tool ('This does not contact anyone'), which distinguishes it from write-oriented siblings like create_request or update_request_status.

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?

Gives a clear trigger condition — use this when the communication already happened outside the system and needs to be attached to a request. It does not name an explicit alternative or exclusion list, but the sibling set contains no competing 'log correspondence' tool, so the guidance is sufficient in practice.

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