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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so no safety contradictions exist. The description adds valuable behavioral context by enumerating exactly what fields are returned (including the conditional 'was' price for sale items) and explicitly stating that filters can be used without a keyword. This goes beyond the annotations and helps the agent understand the tool's output and flexibility, though it does not describe pagination quirks beyond what the schema's offset field already covers.

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 two sentences, with the core purpose and capability front-loaded in the first sentence. The second sentence expands on filter behavior with concrete examples, and every phrase earns its place—no filler or repetition. It is appropriately sized for the tool's complexity and maintains a clean structure that is easy to scan.

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 description covers the essential usage patterns (keyword and/or filters), return fields, and the ability to combine filters without a keyword. The tool has 8 parameters, all optional, and the description provides illustrative examples that help an agent understand how to combine them. Since an output schema is present, the lack of detailed return-value documentation is acceptable. The description is complete enough for an agent to correctly invoke the tool in common scenarios, though it could briefly mention the default limit or pagination (already in schema), so it earns a 4 rather than 5.

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 description coverage is 100%, with every parameter individually documented in the schema. The tool description adds extra semantic value by explaining that filters can be combined and used without a keyword, which is not fully captured in the schema's per-parameter notes. This enriches the meaning beyond the raw schema, particularly for the interplay of filters. Given the high schema coverage, this extra guidance justifies a score above the baseline of 3.

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 begins with a specific verb ('Search') and a clear resource ('this store's products'), and specifies the ability to search by keyword and/or filters. It distinguishes itself from siblings like search_articles and list_products by explicitly stating it searches products and lists the return fields (titles, prices, availability, image, URLs). No ambiguity remains about what this tool accomplishes.

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 provides concrete examples of when to use filters without a keyword (e.g., on_sale=true alone, price_max with in_stock_only=true), guiding the agent on valid usage patterns. It does not explicitly contrast with sibling tools like list_products, but the presence of filter combinations and the keyword-optional behavior clearly implies this is the go-to search tool when filters are involved. The guidance is helpful and actionable, but stops short of stating when not to use it in favor of alternatives.

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