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

Annotations only cover the safety profile (readOnly, non-destructive); the description adds the substantive behavior an agent needs: the return anatomy (html/text plus sender and companyControlled/howToChange), the field-provenance rule, and the fallback rule for missing values. It also effectively documents output structure, which matters since there is no output schema.

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?

Front-loaded with the return value, then the operational guidance, and every sentence carries a rule (provenance, no-guessing, company-controlled parts). The middle stretch is dense and slightly run-on, which costs a point but not comprehension.

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 no output schema and only two optional parameters, the description supplies everything an agent needs: the returned fields, how to use them, the mode and signature selectors, the missing-field policy, and where to go to modify the signature. Nothing material is left out.

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 already 100%, so the baseline is 3, but the description adds real meaning beyond it: it spells out what mode "short" actually yields (name, role line and one link) and constrains signature to "me" or an AI assistant/company AI agent sourced from list_signatures. It does not, however, explain how an agent id vs name is resolved.

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 (returns the signed-in person's saved email signature) plus the payload shape (html and text, sender fields), immediately distinguishing it from siblings like list_signatures and update_my_signature. An agent can tell what it gets and why without opening the 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?

Explicit when-to-use (append after the body in place of a sign-off), how to source sender details, what to do when a field is missing (leave it out and say so, never guess), when to ask (if it's unclear which signature), and the alternative for changing it (update_my_signature). No inference required.

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