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

readOnlyHint=true already establishes the safety profile, and the description adds a genuinely useful behavioral caveat: width and height filters are evaluated as independent maximums, not as validated combinations. The return-field list adds little because an output schema already exists, and there is no mention of result limits or empty-result behavior.

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?

Three tight sentences with the preferred-usage claim and the filter axes front-loaded, then the return shape, then the caveat. No wasted clauses, though the 'width/drop' terminology adds slight noise against the schema's naming.

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?

The output schema covers return values, so omitting detail there is fine, but the description never addresses result count limits, pagination, or what happens when no products match the independent-maxima filter. For a 4-parameter discovery tool that is otherwise well explained, these are the remaining gaps.

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 only 25% (only category is described), so the description must compensate: it clarifies that colour matching is partial and that the mm parameters act as independent maxima. However, it uses the vocabulary 'width/drop' and 'required supported', which does not cleanly map onto the schema's max_width_mm / max_height_mm names, leaving ambiguity about whether these are maximums or requirements.

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?

Names a concrete resource (catalog) and the exact filter axes (category, partial colour, width/drop in mm), and calls itself the 'preferred structured discovery' path, which hints at its place relative to search siblings. It stops short of naming search_catalog or search_products to draw a crisp boundary, so differentiation is implied rather than explicit.

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?

'Preferred structured discovery' signals when to reach for this over the free-text search siblings, and the closing sentence explicitly routes the agent to get_price when an exact width/height pair must be confirmed. No explicit when-not conditions beyond that handoff.

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