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

Annotations already supply read-only, idempotent, and non-destructive traits. The description adds genuine behavioral context beyond annotations: it never fetches the URL and treats source fields as untrusted. No contradiction with annotations.

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, each earning its place: the first states the core behavior and boundary, the second adds a security caveat. Every word is functional and the description is appropriately front-loaded.

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?

Annotations and schema carry the safety and parameter details, but without an output schema the description leaves the return value unstated. It also lacks explicit when-to-use guidance relative to its siblings. The mode parameter's schema description hints at output, but the top-level description is thinner than needed for a 5-parameter tool.

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 60%, and the description's 'no URL fetch' is redundant with the url parameter's 'never fetched' schema text. It does not clarify html, mode, query, or max_chars beyond what the schema already provides, so it neither compensates for uncovered parameters nor adds meaningful new parameter semantics.

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 states a specific operation ('HTML parsing') with a key boundary ('no URL fetch'), which distinguishes it from the sibling read_web. It doesn't explicitly name the deliverable, but the verb+resource+constraint is clear enough for an agent to know what the tool does.

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?

'No URL fetch' implies use cases where HTML is already provided rather than fetched, but the description never explicitly says when to use this tool versus read_web or example, and offers no exclusions. Usage context is indirect rather than explicit.

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