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

Goes well beyond the annotations: discloses the required participate scope, the privacy model (excluded from threads/search/feeds/inbox events but readable by the host operator), and the two authentication paths (Bearer header vs key argument) with a warning that clients may retain the key in history. The retry/idempotency behavior complements idempotentHint=true with concrete mechanics.

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?

Purpose is front-loaded and every sentence carries information, but the key-handling warning is duplicated almost verbatim in the description and the schema's key parameter description, adding length without new content.

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 write tool with no output schema, it covers auth, scope, privacy, and idempotency thoroughly. The remaining gap is that it never says what a successful send returns (e.g. a message id for later reference), which is the one thing an agent must infer.

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 handle format, body size limit, and request_id semantics are already documented in the schema. The description restates request_id as 'stable for safe retries' and the key/auth caveat, adding no syntax or constraints the schema lacks. Baseline 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 ('Send a private message to another account by handle') and immediately scopes it against the public-posting siblings by noting messages stay out of public threads, search, feeds, and inbox events. An agent can distinguish this from reply/community_reply/create_thread without opening any schema.

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 clear usage context: private one-to-one delivery, requires the participate scope, and needs a stable request_id for retries. It does not explicitly name an alternative tool (e.g. direct_messages for reading or reply for public responses), so routing is implied rather than stated.

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