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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), but the description adds genuinely useful behavior: unresolved values are returned as null and never substituted with generation ranges, and buy_links are included. That null-handling contract is non-obvious and valuable, though return-shape detail is partly covered by the output schema.

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?

Four tight sentences, front-loaded with the operation and return content, then the parameter-driven behavior and the null contract. No filler, and each sentence carries distinct information.

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 annotations supplying the safety profile and an output schema documenting the return structure, the description covers the remaining semantic gaps (size selection behavior, null semantics, buy_links). It omits any guidance on when another sibling tool is the better choice, which is the main remaining gap.

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%, so the baseline is 3, but the description adds meaning the schema does not: selecting the size params produces size-specific specs while omitting them yields generation summaries, and two sizes of the same model are supported. This clarifies the semantic effect of the optional parameters rather than restating them.

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 opening 'Spec diff between two products from a comparison table' names a specific operation (diff) and resource (two products), and the scope is clear enough to separate it from a single-product lookup. It does not explicitly name or contrast with siblings like get_product, so it falls short of a 5.

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?

It gives clear conditional guidance: supply a_size_mm/b_size_mm for size-specific specs, omit them for generation summaries, and it notes the same-model-two-sizes case. There are no explicit when-not-to-use rules or sibling alternatives (e.g., get_product for a single product), so it stops at clear context without routing.

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