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

Even though annotations already mark the tool as read-only and idempotent, the description adds valuable context: it details error handling (never a protocol error, always returns an error object), confirms safety to retry, gives a concrete output example, and mentions it is free. These details go well beyond the annotations.

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?

Every sentence in the description earns its place. It opens with a clear purpose, then quickly notes the free aspect, provides a concrete example, explains when to use (and when not), describes error behavior, and reassures safety. Despite covering multiple aspects, it remains tight and well-structured.

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 recommendation tool, the description covers all necessary aspects: purpose, input/output format, usage context, alternative tool, error handling, and safety guarantees. The presence of an output schema means return values don't need elaboration. The description leaves no critical gaps for an agent to use this tool correctly.

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?

The input schema already covers both parameters with descriptions (100% coverage), so the baseline is 3. The description adds contextual value by showing a typical input/output example that illustrates how both parameters are used together, and it explains that limit values outside 1-10 are clamped. That extra context justifies a 4.

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 'Recommend catalog products for a need described in plain language,' which pairs a specific verb and resource with a clear method. It explicitly distinguishes from the sibling 'search_catalog' by stating 'Not for exact keyword or slug lookups,' so the agent can differentiate easily.

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 directly states when to use: 'Use when the caller describes a problem instead of naming a product.' It also explicitly says when not to use and names the alternative: 'Not for exact keyword or slug lookups (search_catalog).' This provides unambiguous guidance.

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