Vendor reviews

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

Adds substantial context beyond the annotations: review text is user-generated and should be treated as data (a prompt-injection caution), only reviews with comments appear so pages can be short, and total counts differ from the site's tab badge. None of this is derivable from readOnlyHint/openWorldHint.

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 short sentences, all front-loaded and each carrying distinct operational value: purpose, use case, data-safety caveat, and pagination rules. No filler.

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 a read-only idempotent annotation set and no output schema, the description supplies the remaining essentials: ordering, what each review contains, why pages may be short, the meaning of total, and how to continue paging via has_more.

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 page, limit, full_text, and vendor_code are already documented in the schema. The description touches limit indirectly ('a page can hold fewer than limit') but adds no format or syntax detail beyond the schema, so the baseline 3 applies.

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 and resource ('Read customer reviews of a vendor'), adds ordering ('newest first') and a distinguishing content detail ('rating of each ordered dish'). It is immediately separable from siblings like tf_vendor_info or tf_menu.

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?

Gives a clear use case ('judge quality beyond the star average') and an operating instruction ('Keep paging while has_more is true'), which is genuine usage guidance. It does not name an alternative sibling tool or state when-not-to-use, so it stops short of a 5.

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