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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the exact return fields and the negative constraint 'Moda publishes no prices,' which prevents the agent from promising price data. It omits failure behavior for unrecognized references.

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 with the usage trigger, then the parameter note, then the return shape — a sensible ordering with no filler sentences. The middle fragment 'reference: the reference number as written.' is telegraphic but does carry the normalization instruction, so it earns its place.

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 correctly takes on the burden of enumerating return fields, and it flags the price limitation. For a one-parameter lookup it is nearly complete; the only real gap is whether an unknown reference returns an error or an empty result.

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 the single parameter, so the baseline would be 3. The description earns above baseline by clarifying 'as written,' telling the agent not to normalize or reformat the reference, and by supplying valid-format examples the schema lacks.

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 ('look up a watch reference') and anchors it with concrete example inputs (126610LN, 5711/1A), so the agent knows exactly what class of input triggers it. It implicitly separates itself from find_watch_by_name by requiring a reference number rather than a name, but never names that sibling, so differentiation is inferred rather than stated.

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?

'Use when someone gives a watch reference number' is an explicit trigger condition with worked examples, which is stronger than most definitions. It stops short of exclusions — it doesn't say what to do if the user gives a model name instead (presumably find_watch_by_name) or what happens when the reference is unknown.

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