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

Annotations already provide readOnlyHint=true and openWorldHint=true; the description builds on them by adding the 'public web page' constraint and the concrete output transformations (text-per-selector, clean markdown). No contradiction with annotations exists — the operation is read-only. The description does not mention robots.txt enforcement, but that behavior is fully specified in the acknowledge_robots parameter 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 sentences with zero filler: verb, resource, scope, and both mode behaviors are front-loaded before the category tag. Every clause earns its place.

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 no output schema, the description carries the burden of explaining return shapes, and it does — both modes' outputs are stated. Combined with 100% parameter schema coverage and read-only annotations, the remaining gap (robots.txt default behavior in prose) is covered by the acknowledge_robots parameter description, so nothing an agent needs to invoke the tool correctly is truly 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 description coverage is 100%, so the schema already documents all six parameters, including the mode enum and the REQUIRED conditional on selectors. The description's mode summary adds marginal color but no parameter-level detail beyond what the schema provides, 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?

The description opens with a specific verb+resource — 'Extract structured data from a public web page at a user-provided http(s) URL' — and immediately scopes the tool to public pages, which helps set it apart from siblings like web_fetch and web_extract_table that operate on the same URL space. It does not name any sibling explicitly, so differentiation is implicit rather than stated.

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 description gives clear internal mode-selection guidance ('CSS-selector mode returns text per selector; readability mode returns the main article as clean markdown'), which helps an agent decide which mode to invoke. However, it never addresses when to choose this tool over its siblings (web_fetch, web_extract_table, analyze_readability, convert_url_to_pdf), leaving alternative routing to inference.

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