List Pins on a Pinterest board

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

Annotations already declare readOnlyHint=true, but the description adds meaningful behavioral context: it is 'Read-only, 0 credits,' it mentions timeouts on account-wide listing, and it details the fields returned including promotion status. There is no contradiction with annotations. The description goes beyond the annotation by alerting to performance risks and providing a cost indicator, though it does not elaborate on pagination behavior — but that is covered by the cursor parameter.

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 moderately long but every sentence adds value. It front-loads the core function, then lists return fields, then emphasizes the pinId source, then gives the boardId preference, then states read-only/cost/connection needs. The use of capitals for the pinId note is attention-grabbing but not excessive. It is concise enough for the information density.

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 fully specifies the returned row's fields (id, title, description, destination link, alt text, board, creation date, promotion status). It also covers prerequisites ('Needs Pinterest connected'), cost ('0 credits'), and a performance caveat (timeouts). An agent has everything needed to decide when and how to call it and what to expect, making it a complete description.

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% — each of the three parameters (limit, cursor, boardId) has a clear description in the schema. The tool description does not add much beyond the schema; it reinforces that boardId should be preferred but doesn't redefine parameter semantics. Given the high coverage, 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 clearly states the tool lists Pins, either for a specific board or across all boards when boardId is omitted. It specifies the exact resource (Pins) and identifies the fields returned. It also differentiates from sibling tools like list_pinterest_boards, which list boards, and post_to_pinterest, which creates a Pin — so an agent can distinguish it immediately.

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 explains when to use this tool: it is the source for pinId that other Pin tools need, because post_to_pinterest only returns an id at creation. It also advises 'Prefer passing a boardId' due to known timeouts on account-wide listing, and notes the requirement 'Needs Pinterest connected.' This gives clear, actionable guidance on when and how to invoke it.

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