Suggest Email

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

With no annotations, the description itself carries the disclosure burden. It does well by stating every result is an unverified guess, advising the agent to show it to the user for sanity-checking, and warning that bounces may occur. This goes beyond a generic 'suggest' label and sets accurate expectations.

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 short sentences deliver the core purpose, the inference method, and a practical caveat. There is no filler or redundant restating of the tool name, and the most important information is front-loaded.

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 single-parameter tool with a complete schema and an output schema present, the description supplies all essential context: what it does, how it infers, and how to treat the result. No critical operational detail appears 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?

There is only one parameter, contact_id, and the schema already describes it well by pointing to find_warm_paths or find_alumni. The description does not add much parameter-level detail, but the schema coverage is 100%, so the baseline of 3 is appropriate.

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 names a specific action ('work out a likely work email') and a clear resource (a contact), and distinguishes it from siblings like send_email and set_contact_email by emphasizing that this is a guess based on existing addresses. This is not a tautology and an agent can immediately understand what the tool is for.

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 gives clear context for when to use the tool: when a contact's likely work email is needed and existing address conventions can be learned. It doesn't explicitly name alternatives or exclusions, but the contrast with send_email/set_contact_email is implied strongly enough that an agent can avoid misuse.

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