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

Annotations only say readOnly/openWorld/non-idempotent/non-destructive; the description adds real context beyond that: $0.01 per call, failed calls free, repeats are not free (consistent with idempotentHint=false), attribution/terms-of-use restriction on results, and that the source domain is excluded by default. That is a materially richer behavioral picture than the annotations alone.

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 the core action and return shape, then pricing and constraints. It is dense but nearly every clause carries information; the pricing/terms sentence is long but relevant to a paid tool, so little is wasted.

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 16-parameter tool with no output schema, the description covers what is returned (top 1-20 pages with title, URL, snippet, date), the default filtering behavior, the cost model, and the usage restriction. Nothing an agent needs in order to call it correctly is missing.

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 schema already documents all 16 parameters including defaults and ranges. The description adds only the 1-20 result range, the returned fields, and the default source-domain exclusion, which is modest added meaning over the schema; 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?

"Find pages like a given URL" gives a specific verb and resource, and the following sentence explains the mechanism (read the URL, search on title/topic words) and the output shape (title, URL, snippet, date). No sibling tool in the list does similarity lookup, so it is trivially distinguishable.

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?

Explicit use cases are given: "find competitors, related articles or alternatives to a page," plus a concrete example call. What's missing is any when-not guidance or pointer to an alternative (e.g. a keyword search tool), but with no competing sibling this is a minor gap.

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