draft_site

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description reinforces this with 'Never writes the config' while disclosing what probing actually does (robots.txt, llms.txt, sitemap, framework detection) — real behavioral context beyond the hints. It stops short of covering failure modes or network cost/rate limits for the probe.

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?

Front-loads purpose and the no-write guarantee, then moves through the two modes, the overrides format, and the recommended workflow. Dense but zero filler sentences; every clause carries operational information.

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 4-param tool with a nested free-form object and an output schema present, the description supplies the missing pieces: overrides field naming/format, the meaning of the preview, and the explicit handoff to save_site. Return-value details are correctly delegated to the output schema.

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 does add value for `overrides` — naming concrete config field names (content_selector, allowed_path_prefix, disallowed_path_patterns, max_depth) and the duration string format ('1s') — which compensates for the nested object having no defined properties, but url/site_key/preview_url semantics are already fully covered by 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?

States a specific verb and resource ('Draft a site entry and preview one page extracted with it') plus a negative scope clause ('Never writes the config'). This clearly separates it from the sibling save_site, which is named explicitly as the follow-up step.

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 branching rule: with `url` it probes a new docs site the way `doc-scraper add` does; with only `site_key` it starts from an existing configured entry without probing. It also states the full iteration loop (judge preview → re-draft with overrides → pass entry to save_site), naming the alternative tool that commits.

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