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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds the shape of the result (status, pages scanned, severity counts), but says nothing about ordering, how far back 'recent' reaches, or pagination behavior.

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?

A single compact sentence with the key returned fields front-loaded and no filler. It is arguably under-specified rather than over-long, but for its size nothing is wasted.

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 zero-required-parameter read-only lister with full schema coverage and rich annotations, the description covers what the tool returns. It leaves gaps on recency window, ordering, and how this differs from get_scan_status/get_results, which matters in a 30+ sibling tool surface.

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 description coverage is 100% — both limit (default 10, max 50) and project_id are documented in the schema. The description adds no parameter meaning beyond the word 'recent', 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?

The description names the resource (recent site scans) and the fields returned (status, pages scanned, severity counts), which is enough to tell it apart from single-scan tools like get_scan_status. It is a noun phrase rather than a verb-led statement, and it doesn't explicitly contrast with sibling listers, so it stops short of 5.

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?

There is no guidance on when to call this versus alternatives such as get_scan_status, get_results or start_scan. The agent must infer usage purely from the name and the word 'Recent'.

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