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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: a hard 200-heading result cap and a free-mode note (no key, credits or wallet). It still says nothing about the nested input shape or failure behavior.

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 short sentences with the core action front-loaded; each carries a distinct fact (cap, free mode, no auth, limits). 'No key, credits or wallet' is slightly redundant but clarifies the free-tier claim.

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?

An output schema exists, so return values need not be described, and the annotations carry the safety profile. The description covers scope, cost, and limits; the only real gap is that the nested input.html parameter is left undocumented.

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 67%, so requestId and maxPriceMicroUsd are already documented as ignored legacy fields in the schema. The description does not explain the required nested input.html (a 100,000-char HTML string) at all, adding only the vague 'input limits apply' clause.

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 verb ('Extract') and resource ('headings') and even qualifies the output (parent indices, skipped-level indicators) plus a 200-item cap. The resource is distinct enough from siblings like html_metadata, html_links, and html_tables that an agent can tell it apart, though 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?

There is no statement of when to choose this tool over html_metadata or the other html_* extractors, nor any exclusions. The 'FREE during validation' and 'input limits apply' lines describe cost/constraints, not usage selection.

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