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

Annotations declare destructiveHint/openWorldHint but say nothing about side effects. The description adds non-obvious behavior: messages reach a real person, and operator sends pause the bot on that conversation 'exactly as if a human had replied from the app.' That is genuine value beyond the structured hints.

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?

Three sentences, front-loaded with the core action, then the risk, then the required behavior. No filler and each sentence carries a distinct load.

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 mutation tool with no output schema and 7 parameters, the description covers the essential risk profile and confirmation requirement. It does not describe the return value (message id, delivery status), which is a minor gap given no output schema exists.

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 57%; the notable parameters (buttons, accountId, attachmentUrl, idempotencyKey) are already well documented in the schema, including the duplicate-link warning. The description adds no parameter meaning, and the undocumented ones (message, conversationId, attachmentType) are largely self-evident from name/enum. Baseline 3.

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+resource ('Send a message') and scopes it to 'an existing conversation', which implicitly distinguishes it from start_conversation and send_broadcast. It does not name a sibling explicitly, so an agent must infer the routing rather than read it.

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 strong, actionable precondition: 'Ask the user before sending,' driven by the public-facing rationale. It stops short of naming alternatives (e.g., start_conversation for new threads), so the when-to-use-this-vs-that dimension is only partly covered.

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