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

Goes well beyond the annotations: discloses that nothing happens on call, that the response carries a confirmUrl, the 30-minute link lifetime, and the required human confirmation step. This is exactly the context destructiveHint/openWorldHint=true implies but cannot state, and it does not contradict them.

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?

Five short sentences, front-loaded with what the tool does and what does *not* happen. Each sentence carries a distinct operational fact with no repetition.

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?

Despite having no output schema, the description explains the salient return field (confirmUrl), its lifetime, and the required user interaction, plus the critical instruction never to report completion. Nothing an agent needs to invoke and report correctly is missing.

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 both parameters are already documented in the schema. The description only alludes to 'draft invoice' and 'client' without adding format or selection guidance, so 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?

Names a specific two-phase action and its exact resource: preparing an email of a *draft invoice* to the client. The draft-only precondition and the confirm-link mechanism distinguish it from send_quote and send_reminder without needing the sibling schemas.

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 tells the agent how to use the result (give the confirmUrl to the user, it only runs after they press Confirm, valid 30 minutes, never claim it was done). It doesn't name alternative siblings or when not to call it, but the operative guidance is unusually concrete.

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