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

Annotations only declare the generic safety profile (not read-only, not idempotent, not destructive). The description adds genuine behavioral facts an agent could not infer: link previews and email scanners cannot answer, only a button press counts, only the first answer is accepted, and page opens are not recorded.

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 tight sentences: the purpose first, the anti-false-positive guarantee second, the mandatory next call last. No filler and no repetition of schema content.

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?

With an output schema present, return values need not be described, and annotations cover the safety profile. What remains — what the recipient sees, how answers are captured, and the required wait_for_approval follow-up — is all present, so an agent has everything needed to call it correctly.

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% and each property carries its own description (title, choices with default, message, inbox_key origin), so the schema does the heavy lifting. The description's 'your title, message and one button per choice' largely restates what the schema already says, so the 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?

States a concrete verb+resource ('Make a link') and immediately scopes it ('to send a person when you need their decision'), then explains what the link renders. An agent can distinguish this from create_inbox or set_response without opening any schema.

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 clear trigger condition ('when you need their decision') and explicitly names the required follow-up step: 'Then call wait_for_approval.' It is not fully specified as when-not-to-use guidance (e.g., it never contrasts with set_response for programmatic answers), but the sequencing guidance is unusually actionable.

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