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

Annotations only provide generic hints (readOnlyHint=false, destructiveHint=false), so the description carries the behavioral burden and does so well: it discloses refusal behavior, draft-vs-send outcomes, the 'via <your app>' recipient disclosure, and explicit privacy constraints on salary/contact/private life. Minor gap: it doesn't state rate limits or the shape of the confirmation returned.

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?

A single dense paragraph that is front-loaded with the core action and two targeting paths before moving to behavioral rules and privacy limits. Every sentence carries operational meaning; nothing is decorative or redundant.

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 non-idempotent write tool with four parameters and an output schema, the definition covers the target selection, mode semantics, permission gating, draft fallback, and privacy boundaries. Return values are legitimately omitted because an 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 100%, so the baseline is 3, but the description adds real preconditions beyond the schema: 'to' requires that the target has turned their professional profile on, and 'mode: "draft"' is prescribed as the fallback when rules are exceeded. These tie parameters to decision logic rather than restating field docs.

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 (write as the person's professional self) and immediately enumerates the two distinct targets: answering a professional conversation (conversationId) or posting to another person's professional profile (to). This clearly distinguishes it from siblings like send_message, message_group, and send_to_conversation.

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?

Explicitly describes the decision tree: depending on the person's level the action is refused (off), saved as draft (draft), or sent (send), and it names the governing artifact (pro_profile → rules). It also gives a clear fallback rule — make it a draft when a message exceeds standing rules — leaving nothing to inference.

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