Read a whole site

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

With no annotations, the description fully shoulders the burden of behavioral disclosure. It honestly reveals the 60-second wait, the job-id fallback for long runs, per-page billing with a cap, and the result_url for the full output. This is far beyond minimal and gives the agent accurate expectations.

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 sentences, front-loaded with the core purpose, followed by cost and async behavior. Every sentence earns its place—no filler or repetition.

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 tool with no output schema and no annotations, the description covers all essential aspects: input (seed URL), scope (same-domain), output (markdown + result_url), cost, and long-run handling. An agent has enough information to invoke the tool and interpret 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 'capped by limit' and cost context, but the schema already states 'Max pages (default 100) — bounds cost at limit × $0.005.' Therefore the description adds minimal incremental meaning beyond the schema.

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 'Crawl same-domain pages from a seed URL into markdown,' a specific action on a resource that clearly distinguishes this tool from siblings like scrape_page (single page) and check_job (job status). The title 'Read a whole site' reinforces the purpose without ambiguity.

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 provides clear context on when to use the tool (for whole-site crawling) and mentions async fallback via check_job if execution exceeds 60 seconds. It does not explicitly name alternatives or state when not to use it, but the context is sufficient for an agent to select it appropriately among siblings.

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