compare_products

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is safe and non-mutating. The description adds value by disclosing error handling behavior: it lists how unknown ids (`not_found`) and malformed ids (`invalid`) are returned in the response. This goes beyond the annotations and is useful for the agent. It doesn't mention limits like pagination or timeouts, but given the output schema exists, this is sufficient. No contradiction found.

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 compact and well-structured. The first line summarizes the core function, followed by a clear list of what's included per product, and ends with error handling notes. Every sentence earns its place, no fluff, and the most important constraint (up to 20, one city) is front-loaded.

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?

Given the tool's moderate complexity (2 params, batch operation) and the presence of an output schema and comprehensive annotations, the description is complete. It covers input constraints, call semantics (one request), and error handling. The output schema presumably details the response structure, so the description doesn't need to. An agent has all necessary information to call this 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?

Schema description coverage is 100%, so the schema already documents both parameters (city and products) with detailed descriptions, including format and defaults. The tool description adds contextual value by clarifying that one request covers all products and mentions error fields, but it doesn't add new parameter-specific semantics beyond what's in the schema. Thus, a baseline 3 is appropriate; the description doesn't need to repeat schema details.

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 clearly states the action 'compare products' with the resource 'up to 20 products side by side for one city', and details the comparison dimensions. It distinguishes itself from siblings like get_product by implying batch comparison across multiple products, though it doesn't explicitly name a sibling. The specific fields listed (rating, prices, delivery, etc.) make the purpose unambiguous.

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 specifies the scope (one city, up to 20 products) and input format (product ids, M-ids, URLs), which implies when to use it (batch comparison). It doesn't explicitly state when not to use it or name alternatives, but the context of sibling tools (e.g., get_product for single product) provides implicit guidance. A clear exclusion or mention of get_product would push to 5.

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