Audit supplied HTML offline

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: no network requests are made and HTTP status checks will remain unknown, which tells the agent what the audit result cannot contain.

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, front-loaded sentences with no filler. The offline constraint and result limitation appear early, before the url clarification.

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 and only two required parameters, the description covers the critical semantics: input source, no network access, unknown HTTP results, and the role of the base URL. It is complete enough to call correctly, though it never routes the agent between this and audit_url.

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 0%, so the description must carry the parameter burden, and it does: it clarifies that 'url' is a base URL used only to resolve links (not a page to fetch) and that 'html' is the user-supplied markup to audit. This disambiguates the otherwise opaque uri-typed url parameter; only the length limits remain undocumented.

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 names a specific verb (audit) and resource (user- or pipeline-supplied HTML), and 'Makes no network requests' implicitly separates it from the sibling audit_url, which must fetch over the network. It does not name the sibling explicitly, so differentiation is inferred 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?

'HTML supplied by the user or a build pipeline' implies the offline-input scenario, but the description never states when to choose this over audit_url (e.g., 'use when you already have HTML; use audit_url to fetch a live page'). Usage is implied rather than directed.

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