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

Annotations already declare readOnlyHint, openWorldHint, and non-destructive behavior, so the safety profile is covered. The description adds genuinely new value by characterizing the output fidelity ('headings, tables, code blocks, and links intact', 'token-efficient'), but omits rate limits, size limits, and failure modes such as paywalls or client-rendered content.

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?

A single well-formed sentence with the core action front-loaded and no filler. It is efficient, though it packs the output-fidelity details into the same clause rather than separating purpose from output characteristics.

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 two-parameter, no-output-schema tool, the description conveys both the input scope ('public URL') and the shape of the return value ('Markdown with headings, tables, code blocks, links'), which an agent needs. It falls short only on operational limits and failure behavior, which are minor for this complexity.

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%, with both url and api_key documented in-schema, so baseline is 3. The description adds no format constraints, URL normalization rules, or guidance on when the optional api_key is worth supplying.

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 gives a specific verb ('Extract') and resource ('Markdown from any public URL') and enumerates the preserved structures, so the agent knows exactly what it produces. It does not distinguish itself from the generate_* siblings, which also emit Markdown, so differentiation is left to inference.

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 phrase 'any public URL' implicitly bounds usage and the schema's api_key note hints at rate-limit escalation. However, there is no explicit when-to-use versus the generate_content_md/generate_links_md siblings and no statement of when not to use it (e.g., auth-gated or JS-rendered pages).

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