website_content

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

Annotations declare openWorld, idempotent and non-destructive, but the description adds genuinely non-obvious traits: no JavaScript rendering, truncation can leave the page incomplete, sources' rights must be respected, and returned page content is untrusted data rather than instructions. The sandbox note ('returns dummy data, no payment') is useful but ambiguous about production billing. This is substantially more than the annotations provide.

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 key facts are front-loaded, but the text repeats itself: 'No JavaScript rendering' appears twice, and the return fields are listed once as a sentence and again after 'Returns: JSON with ...'. The sandbox and trust-warning lines are justified, but the duplication costs it a point.

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, so enumerating the return keys (url, fetched_at, http_status, title, text, headings, links, truncated, content_hash, snapshot) is essential and is done. It also covers the main failure mode (truncation) and the safety caveat about untrusted content. Only the edge cases of failed fetches and what http_status values imply are left implicit.

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?

There is a single parameter with 100% schema description coverage, including the constraint that IP addresses, ports and credentials are rejected, so the schema already does the work. The description restates only 'one page' / 'public links' and adds no format or syntax detail beyond the schema. Baseline 3 applies.

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 opening sentence gives a specific verb and resource: extract bounded main-topic text, headings and public links from one page, returned as JSON. It also states the scope limit (single page, no JavaScript rendering). It does not name or contrast with likely siblings such as page_audit, website_check or website_changes, so an agent must infer the boundary.

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?

Usage is only implied: 'from one page' and 'main-topic text only' suggest a content-extraction scenario, and the sandbox note signals a development context. There is no explicit statement of when to prefer this over page_audit or website_check, and no prerequisites or exclusions beyond rejected URL forms (which live in the schema).

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