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

The description itself is rich — consent refusal returns the consent page URL, robots.txt is obeyed, a draft must exist before import_images, images are capped at 20 / 5 MiB, and calls count against the daily plan limit. However, it describes fetching arbitrary external websites and ingesting 'data written by other people', which conflicts with the declared openWorldHint=false. That inconsistency is flagged, though the surrounding disclosure is otherwise strong.

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?

The core verb and resource are front-loaded, but the body is one dense run-on paragraph mixing return shape, consent flow, image limits, rendering fallback and plan quotas. Content earns its place individually, but the lack of structure makes it hard to scan, and the appended generic safety paragraph repeats the read-only-of-external-data idea.

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, the description still spells out the returned page structure (title, description, lang, headings, nav, text blocks, forms, links, image URLs) and the failure shapes (consent refusal, render.reason). For a six-parameter fetch tool with prerequisites, this is complete enough to call correctly.

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, but the description adds real meaning beyond the schema: import_images downloads up to 20 pictures of named formats and sizes into the draft's candidates with source_url and requires an existing draft; render 'auto' triggers headless rendering and reports failure via render.reason; purpose is tied to the recorded consent. Only 'pages'/'site' get no extra treatment, which the schema already handles.

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 and resource ('Read an existing website'), the scope of the read (same-origin pages, robots.txt, plan page count) and enumerates what is returned. It also explicitly names the sibling that replaces it for already-published sites ('start from it with restore_draft'), so an agent can distinguish it 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?

Gives an explicit prerequisite (request_fetch_consent must have been agreed in the browser), an explicit prohibition ('Never fetch a site the person does not own or have permission for'), an explicit alternative (restore_draft / list_versions for Siteon-published sites), and the fallback path when rendering fails. When-to-use versus when-not-to-use is fully covered.

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