list-persons

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

With no annotations, the description carries the full burden. It discloses that unidentified faces appear as _UNKNOWN_ and that results are sorted by photo count, adding behavioral detail beyond the schema. It doesn't explicitly mention read-only status, but for a list operation this is a minor omission.

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 uses a structured format with 'Use when', 'Returns', and 'Do not use when' headers, front-loading the purpose. Every sentence contributes, and there is no wasted wording.

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 list operation with an output schema, the description covers the use case, return format, behavioral quirks (_UNKNOWN_), and exclusions. The tool is fully contextualized for an agent to select and invoke 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 description coverage is 100%, so baseline is 3. The description adds 'Pass limit for the top-N' which reinforces the limit parameter's purpose, but it doesn't meaningfully expand on the library parameter beyond what the schema already states.

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 clearly states the tool returns a catalog of named people from Photos face recognition, with specific use cases like discovering person names and seeing photo counts. It distinguishes from sibling tools by referencing the person filter in query and list-keywords.

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?

Provides explicit 'Use when' and 'Do not use when' sections, naming exact alternative tools (query with person filter, list-keywords) and describing appropriate contexts, such as discovering exact names before querying.

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