get_reviews

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

Annotations already mark this as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds valuable behavioral context beyond annotations by explaining that the tool returns both the star split from the feed and the merged group's rating, and that the feed may contain fewer ratings than the card counts. This nuance about potential data discrepancies is exactly the kind of behavior an agent needs to know, making it a strong supplement to 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?

The description is two short paragraphs. The first sentence immediately states the core function and output fields. The second paragraph adds a crucial clarification about rating sources and discrepancies in a compact, front-loaded manner. Every sentence earns its place, with no redundancy or filler. This is an excellent example of concise, structured documentation.

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 (6 parameters, enums, and a subtle rating nuance), the description is thorough. It explains the output fields, the star-split and group-rating distinction, and the difference from get_product's card rating. The output schema exists, so return format details are covered there. The only minor gap is not explicitly mentioning how pagination or limit works, but the schema's limit parameter and the tool's read-only nature make that less critical. Overall, it's complete enough for an agent to call 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 67% (4 of 6 parameters have descriptions). The description itself does not elaborate on any input parameters—it only lists output fields. For the two parameters lacking schema descriptions (max_rating, min_rating), the description offers no additional clarity, though their constraints are self-explanatory. Since the schema covers most parameters and the description adds no parameter-specific meaning, a baseline score of 3 is appropriate.

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 a precise statement of the tool's function: 'Buyer reviews with date, stars, text, pros, cons, bought variant and seller reply.' It clearly names the resource (reviews for an article) and the specific data fields returned. It also distinguishes itself from the sibling get_product by explaining that the card rating (from get_product) is the one shown on the site, which disambiguates which rating a headline refers to. This makes the purpose unmistakable.

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 clear context about when to use this tool versus get_product: it explicitly states that the feed may hold fewer ratings than card counts and that get_product provides the site-displayed rating. This gives the agent a concrete reason to choose one tool over the other for rating-related queries. However, it does not explicitly state 'use this tool when you need detailed review text' or list other exclusions, so it's slightly shy of a perfect score.

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