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

Annotations already declare readOnly/openWorld/destructive hints, but the description adds real context beyond them: it will not fetch the images (no outbound network work), it is free with no key, credits or wallet, and result count is capped at 200. It does not discuss failure modes or what happens with malformed HTML.

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?

Three short sentences, front-loading the extraction scope before the cost and limit notes. No filler or repeated 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?

An output schema exists, so return-format detail is unnecessary, and the description still names what is extracted. Cost/pricing and the item cap are covered; the only gap is input parameter semantics such as baseUrl.

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 only 67% and the description contributes nothing about inputs. Notably baseUrl — which determines how relative image sources are resolved — is undocumented in both the schema and the description, so an agent gets no help here.

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 ('Extract ... image URLs, alt text and source attributes') and bounds the output ('up to 200'). The clause 'does not fetch images' implicitly separates it from the web_* fetch siblings, though no sibling is named explicitly.

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 no explicit when-to-use or when-not-to-use guidance and does not name an alternative such as html_links or web_readable_fetch. Usage is only implied by the extraction verb, plus a vague 'Existing source and input limits apply'.

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