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

The description adds meaningful behavioral context beyond annotations: 'Saves the draft on the prospect' (persistent mutation), 'returns it' (output), and 'Does not send' (critical side-effect disclosure). Annotations only state readOnlyHint=false and destructiveHint=false, so this extra detail is essential for safe invocation.

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 concise sentences each add value: main action, side effect, and exclusion. Front-loaded with what the tool does first, followed by important caveats. No filler or redundancy.

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 tool without an output schema, the description's 'returns it' is vague about whether the return is the full text, a draft object, or an ID. The schema marks all parameters as optional, but the description implies a prospect is needed, and it doesn't explain how prospectId vs linkedinUrl relate. The regenerate parameter and its caching behavior are not addressed, leaving an agent uncertain about when to set it.

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 only 40% schema description coverage, the description partially compensates: 'in their language' maps to the language parameter, 'built from their detected signals' adds context to signalIndex. However, prospectId, linkedinUrl, and regenerate are not explained; the description doesn't clarify that regenerate bypasses cached drafts or what linkedinUrl is used for. This leaves meaning gaps for 3 of 5 parameters.

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 tool drafts a personalised email for a prospect, using detected signals and language. It distinguishes itself from send_email by explicitly noting it does not send, and from draft_linkedin_message by focusing on email. The verb 'write' and resource 'email for a prospect' are specific and actionable.

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 this tool: when you need a draft to review or later send. The explicit 'Does not send' serves as a clear exclusion, indicating send_email should be used for sending. However, it doesn't directly name sibling alternatives or provide explicit when-not-to-use conditions beyond not sending.

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