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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral detail well beyond them: 10 reviews per page, locale governs summary/label/review language, an unrecognized topic yields a 400, and a model with no reviews or an unrecognized model_number returns an empty list rather than an error. These edge-case behaviors are exactly what an agent needs and cannot infer from 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?

Front-loaded with what is returned, then the identifier disambiguation, then filters and edge cases. Dense and mostly waste-free, though the long enumeration of summary components and scale labels runs slightly long.

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 5-parameter read tool with full schema coverage, annotations, and an output schema, nothing an agent needs in order to call it correctly is missing. Identifier sourcing, pagination, filter semantics, locale effects, and failure behavior are all covered.

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 genuine disambiguation: model_number is the Adidas model number and is explicitly NOT the SKU in products[].id. It also clarifies that rating filters to a single star level and locale changes review language, though the 10-per-page detail is already in the schema.

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?

States a specific verb (retrieve reviews) plus the exact resource and scope: reviews for ONE product model together with its rating summary. It even enumerates the summary contents (overall rating, histogram, recommend %, per-attribute averages, AI digest), so an agent can distinguish it from adidas_product and adidas_product_review_topics without opening a schema.

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?

Explicitly tells the agent to source model_number from an adidas_search result's products[].model_number and where to read valid topic values (product/review-topics). It stops short of naming sibling tools as alternatives ('use X instead') and gives no when-not-to-use exclusions, but the retrieval flow is clear.

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