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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description's only extra behavioral signal is 'in one call', which conveys batched retrieval; it says nothing about fetch failures, robots.txt handling, or size limits (those live in the schema).

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?

Two short sentences, front-loaded with the outputs and input types, followed by the one actionable hint. No filler, though the second sentence is thin and could carry more routing value.

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 zero required parameters, a fully documented schema, and annotations covering safety and open-world access, the description gives enough to call correctly. For a tool with no output schema, it could clarify the returned object shape, but the enumeration of parts largely covers that.

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 the schema already documents url, html, include, maxChars and mainContentOnly thoroughly. The description adds only a pointer to include, duplicating what the schema says; baseline 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?

States a specific operation: extracting markdown, metadata, links and headings from a URL or HTML in a single call. The output list and 'in one call' phrasing implicitly differentiate it from narrower siblings like page_to_markdown and page_metadata, but 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?

'Use include to choose parts' is guidance on a parameter, not on when to pick this tool over page_to_markdown or page_metadata. The combined-output framing implies this is the tool for multi-part extraction, but the description never states exclusions or alternatives.

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