Find someone's address

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

Annotations already provide readOnlyHint/openWorldHint/destructiveHint, and the description adds useful behavioral context: results may contain multiple people, the returned email is a 'real' address, and the agent must not guess addresses. This goes beyond the structured annotations without contradicting 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?

Three sentences, each earning its place: the first defines the core operation, the second gives an imperative usage rule, and the third resolves ambiguity. The description is front-loaded and concise with no filler.

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 simple one-parameter read-only lookup with no output schema, the description covers invocation, the return value (email address), and the multi-result scenario. It does not detail the full response structure, but that is not necessary for the tool's stated purpose.

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 the only parameter 'name' is described as 'a name, or part of one.' The description reiterates this by saying 'by name or partial name,' but it adds no additional semantic detail such as matching rules, case sensitivity, or input constraints. Baseline 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 states a specific action ('Look up a person by name or partial name') and the expected outcome ('return their real email address'). It clearly distinguishes this tool from its siblings, none of which perform person resolution.

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 explicitly states when to use the tool: 'ALWAYS use this before addressing a message or inviting someone.' It also provides a behavioral rule for ambiguous results ('ask which one rather than picking') and a strong safety directive ('Never type an email address you were not given').

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