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

Annotations only declare readOnlyHint; the description adds substantial behavior beyond that: which elements are discarded, truncation at maxChars with a visible marker, no JavaScript execution so SPAs return an empty shell, and table flattening. These are exactly the failure modes and output-shape facts 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?

Three dense sentences with zero throat-clearing. Safety and mutuality constraints are front-loaded, then output scope, then limitations – a sensible order for an agent scanning before invocation.

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 read-only converter with no output schema, the description supplies the return type ('text'), the truncation behavior, and the JS limitation that determines whether the tool is even viable for a given page. The empty-shell warning on SPAs is the kind of edge case that otherwise causes silent bad results.

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 baseline is 3. The description adds two things beyond the schema: it reiterates the url/html mutual exclusivity as a top-level constraint, and it reveals that maxChars truncation is signaled by an inserted marker, which the schema does not say. It says nothing extra about headers.

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 and resource ('Convert ... to Markdown') and then enumerates the exact conversion scope: headings, links, lists, emphasis, code, quotes. It distinguishes itself from the sibling fetch tools by framing both a URL-fetch path and a raw-HTML path, and from fetch_extract by naming what gets stripped.

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?

It gives clear context for when this applies: post-processing a fetched page or converting a string you already have ('one of the two'). It cues the workflow with 'a fetched URL' and the stripped-element list, but never names fetch_html explicitly as the upstream sibling or states when to prefer it over fetch_extract.

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