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

Annotations only cover readOnlyHint; the description carries the real behavioral burden: sanitization of scripts/styles/handlers, absence of JS execution with the SPA consequence, and truncation behavior at maxChars with a marker. These are non-obvious traits an agent needs before calling.

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?

Four dense sentences, each loading information: safety/scope first, then the fetch_extract contrast, then the JS limitation, then truncation. No filler or restatement of the title.

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?

No output schema exists, yet the description characterizes the return value precisely (tag/attribute-preserving HTML with listed elements stripped, truncated with a marker). For a 3-parameter tool with a nested headers object, nothing an agent needs to call it correctly is 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 coverage is 100%, so the baseline is 3. The description adds beyond the schema by noting that maxChars produces a cut with a visible marker, which tells the agent how truncation manifests in output rather than just that a cap exists.

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?

Specific verb+resource ('fetch a page and return its HTML') plus an explicit statement of what is removed (scripts, styles, svg, iframes, comments, inline handlers) and what is preserved. It also names the sibling it is not (fetch_extract) so an agent can discriminate without opening a schema.

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?

Explicitly routes the agent: 'For inspecting or rebuilding markup, not plain text (fetch_extract gives that).' It also gives a negative condition — no JavaScript, so SPAs return an empty shell — which tells the agent when not to use it.

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