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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuine value by confirming no scan is triggered and disclosing the error behavior when no record exists. It does not describe what the record contains, which keeps it from a 5.

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 short sentences, each carrying distinct information: what is returned, what does not happen, and the failure mode. Front-loaded and free of waste.

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?

There is no output schema, so the description must carry the return-value burden, but 'stored scan record' is left largely undefined — no indication of fields, freshness, or shape. It is adequate for calling the tool correctly but leaves a meaningful gap about what comes back.

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% and the single 'host' parameter is fully documented with format examples in the schema. The description adds nothing beyond what the schema provides about the parameter, so the 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?

States a specific verb and resource ('Return the stored scan record for a host') and distinguishes itself from the scan-initiating sibling by saying 'It starts no scan.' However, the name get_score versus the description's 'scan record' leaves slight ambiguity about whether the returned payload is a score or a broader record, and siblings get_report/list_checks are not addressed.

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 starts no scan' implicitly routes the agent to scan_site when fresh data is needed, which is a clear usage condition. It stops short of explicitly naming alternatives such as get_report or stating when a stored record is preferable to a report.

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