Start a website scan

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

Annotations already declare non-read-only, non-idempotent, open-world behavior. The description adds meaningful context beyond that: it consumes the workspace's usage allowance (session and month) and auto-creates a project if needed. That is real behavioral disclosure – cost and side effects – though it omits whether the call blocks, returns a run id, or how long it takes.

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 tight sentences, front-loaded with what is scanned. Every sentence carries information; nothing is padded.

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?

A non-idempotent, quota-consuming scan tool with no output schema and zero parameter documentation. The description covers side effects and quota, which is valuable, but leaves an agent unable to predict return shape (run handle vs inline results) or the role of wait_seconds/max_pages.

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 0%, so the description must compensate for all 4 undocumented parameters (url, max_pages, workspace, wait_seconds). It mentions 'that host' and 'workspace' implicitly but explains none of them: no crawl limit semantics for max_pages, no meaning for wait_seconds, no format guidance for url. This is a major gap.

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 (scans) and resource (website), and enumerates exactly what it checks: broken links, console and network errors, accessibility, and speed. Clearly distinct from sibling run tools like start_run or rerun_failed, which operate on test runs rather than website scans.

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?

Implies usage by describing what a scan does and mentioning workspace project resolution, but never says when to prefer this over start_run or how it relates to wait_for_run/get_run_results. No explicit exclusions or alternative routing.

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