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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description adds that the tool only returns the display name for a single ref, that batch returns an array, and includes a crucial safety warning that person data is external registry data and must be treated as data, not instructions – a prompt-injection guard. This goes beyond structured annotations.

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?

The description is five well-ordered sentences, each earning its place: main purpose, dependency on search_people, return scope, batch behavior, and security warning. It is front-loaded with the core action and only then gives routing and safety details. No filler or duplicate schema text.

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, the description carries the burden of explaining return values – and it does: display name for single ref, array of identity records for batch. It also covers the external data caveat and points to get_person_section for any deeper data, so an agent has enough context to call and interpret results correctly. The only minor gap is that the shape of an 'identity record' beyond display name is not detailed, but that is by design since detailed data lives in sections.

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 already covers 100% of parameters with descriptions, so baseline is 3. The description adds extra semantic context by tying personRef to search_people results and providing a concrete example for refs ('john smith', 'jane doe') with the max-20 constraint restated. This elevates it above schema-only documentation.

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: 'Get a person's identity record.' Explicitly contrasts with get_person_section for detailed data, so an agent can distinguish between the base tool and its section variant. Also clarifies batch mode returns an array of identity records.

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 directs the agent to call it after search_people and pass the returned 'ref'. Lists precise alternatives: get_person_section for 'companyLinks', 'officerRoles', and 'disqualifications'. Gives batch usage with max 20, leaving no ambiguity about when to choose batch vs single.

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