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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is to add context beyond that — and the description delivers richly: empirically measured response sizes (12.5 KB vs 1.6 KB trimmed), exact fields preserved/dropped by trim, shortcode URLs returning 404 at a measured rate (3 of 12), and expectation of 404s on deleted pins. These are behavioral realities the agent could not infer from annotations or schema.

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 dense and logically ordered: purpose → response shape → size/trim tradeoff → sibling routing → failure modes. Every sentence earns its place and the most decision-critical fact (what it fetches, by what URL form) is front-loaded. It loses one point only because the two field enumerations make it longer than strictly necessary given an output schema exists.

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 two-parameter read tool with a full output schema and safety annotations, this description covers every decision an agent needs to make: what the tool does, URL format validation, trim's exact effect, which sibling to use instead, and realistic failure expectations. Nothing an agent needs to invoke this correctly is 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?

Schema coverage is 100% for both parameters, so baseline is 3, but the description goes far beyond the schema's generic 'Pinterest pin URL' and 'trimmed down version'. It specifies the exact URL form expected, the numeric-id requirement and shortcode failure mode for url, and precisely what trim does — which fields survive and which are dropped, plus the size delta. This materially improves an agent's ability to set trim correctly.

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 opens with a specific verb and resource: 'Fetches one pin by URL, of the form pinterest.com/pin/<id>.' It immediately distinguishes this from sibling search tools by emphasizing single-pin-by-URL lookup and explicitly noting the response shape differs from search results. An agent can tell exactly what this tool does and how it differs from get_pinterest_search without opening any schema.

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?

Explicit routing guidance is provided: 'To find pins by keyword use get_pinterest_search; to page through the board a pin sits on use get_pinterest_board.' It also tells the agent when NOT to call (URLs ending in shortcodes) and what to check before calling (numeric trailing id). No other sibling in the list is left ambiguous relative to this tool.

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