check_site

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

With no annotations, the description carries the full behavioral load and does so well: it discloses caching/throttling, the permission constraint, the read-only nature ("no login, no exploit tooling"), and the failure mode where a "blocked" verdict means nothing was graded. The one blemish is internal tension between "one fresh check per site per week" and "Results are cached for a day," which an agent could misread as conflicting rate limits.

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-loaded with the core action, then proceeds through caching, result-relaying rules, verdict semantics, and safeguards. Dense rather than padded, though the relaying/urgency guidance is lengthy and the caching statements could have been merged to avoid the apparent contradiction.

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 the description must describe returns, and it does: a plain-English report card with verdict (enum values clean/attention/urgent/blocked), headline, and per-item what-was-seen/why-it-matters/how-to-fix. Nothing needed to call or interpret the tool is missing.

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% for the single url parameter, so the schema already documents it; baseline is 3. The description adds one genuine semantic constraint — that only the home page is checked — which the schema does not convey.

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?

Opens with a specific verb and resource: "Run EverThread's free security check on a website's home page," and states the observation-only scope. It does not reference the siblings list_findings or explain_finding, so an agent must infer the relationship between checking a site and enumerating findings, but the tool's own function is unambiguous.

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 clear use conditions: only sites the user owns or has permission to check, one fresh check per site per week, and how to behave when a stored result is returned. It never names the sibling tools or explains when to follow up with list_findings/explain_finding, so the workflow context is left implicit.

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