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

Goes well beyond the annotations: it discloses cost ('free'), an explicit rate limit (100 requests/minute per API key), and the size/bound of the result set (last 10 completed/failed). These are exactly the operational facts an agent needs before calling in a loop or at scale.

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, front-loaded sentences: what you get, what it costs, what limits apply. No filler, and the most decision-relevant content (scope of the result) comes first.

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?

With no output schema, the description carries the return-value burden and does most of it: field-level content (scores, errors) and result-count bounds are named. It stops short of clarifying whether the last-10 window is per organisation, per site, or global, which would matter for interpretation.

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?

There are zero parameters, so the baseline is 4. The description confirms there is no filtering surface — it returns 'every' in-flight scan and a fixed last-10 window, which sets expectations the empty schema alone cannot.

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 states a precise resource and scope: every in-flight scan plus the last 10 completed/failed ones, with scores and errors. That is specific enough to separate it from siblings like start_scan or get_site_report, which do not return live run state.

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?

The opening phrase 'What is running right now and what finished recently' implies the polling/status-check use case, but the description never names an alternative (e.g., that start_scan returns a handle, or that get_site_report covers historical data) or states exclusions. Usage is inferable rather than guided.

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