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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description is freed from the safety story. It still adds real context: the exact shape of the returned JSON, the fields per result, and the notable constraint that no prices are published, which prevents a pointless follow-up expectation.

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?

Front-loaded usage condition, then a one-line parameter gloss, then the return shape. Every sentence carries information; nothing is padding.

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 single-parameter lookup with no output schema, the description covers trigger, input meaning, return fields, and the no-prices caveat. An agent could call it correctly and set expectations for the user without any further information.

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%, so 'name' is already documented in the schema as 'A brand, model or nickname'. The description's gloss ('the brand, model or nickname in plain words') restates that, though the nickname examples do help an agent recognize informal inputs. Baseline 3 applies since the schema does the heavy lifting.

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+resource (find a watch) and adds a scope distinction: it is for named watches rather than reference numbers. That contrast alone differentiates it from the sibling look_up_watch_reference without opening either 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?

Gives an explicit trigger condition ('when someone names a watch rather than giving a reference number') with concrete example inputs (Submariner, Daytona, Batman, Moonwatch). It stops short of naming the alternative tool for reference-number lookups, leaving the routing to be inferred.

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