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

Despite annotations lacking readOnlyHint and destructiveHint defaults, the description explicitly states 'Saves the draft and returns it. Does not send.' This discloses the save behavior and non-sending action, which is beyond what annotations provide. It adds behavioral clarity about persistence and side-effects.

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?

Two sentences with clear front-loading of the action and key constraints (language, saves, not sends). Could be slightly more structured but is efficient with no waste. The 'Does not send' is a crucial differentiator placed at the end.

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 simple drafting tool with no output schema, the description covers the core behavior. It doesn't explain return format or the meaning of each parameter, but given the tool's simplicity and that annotations exist, it's adequate. The regenerate parameter is left unexplained, but the description is complete for basic usage.

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?

With 0% schema description coverage, the description must compensate. It mentions 'their language' relating to language parameter, and 'prospect' implying prospectId. It doesn't explain regenerate or linkedinUrl, but the core parameters are implied. Since description covers the main purpose, it partially compensates for the schema gap.

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 clearly states the action (write a short LinkedIn connection note), the input (prospect's detected signals), and the language requirement (in their language). It also explicitly notes it saves the draft but does not send, distinguishing it from send_linkedin_message. This is specific and unambiguous.

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 implies when to use it (when drafting a LinkedIn message for a prospect, not sending) and contrasts with send_linkedin_message. However, it doesn't explicitly state when not to use it or mention alternatives like draft_email, but the sibling list makes it clear it's the LinkedIn-specific drafting tool. Clear context with implicit exclusion.

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