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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so 'Read-only' in the description earns no credit. Beyond that it does useful work: it discloses the sort order (worst first) and the shape of each row (person, vacancy, stage, responsible owner, lateness magnitude), which matters because there is no output schema. It is silent on default limit and whether results are capped or paginated.

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 definition, then the differentiator, then filters — a sensible order. Slightly flabby phrasing ('a number tells you there is a problem, this tells you whose it is') but it earns its place as the sibling distinction.

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 row-content sentence does the heavy lifting and largely covers the return value. Remaining gaps are limit/default behavior and what 'stage SLA' is measured against, but for a read-only filtered list tool this is close to complete.

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 0%, so the description must carry the parameter burden. It names three of four parameters and assigns them the 'filter' role, which is minimal but real added meaning; however it does not explain what filtering by canonical_stage means for a stuck-on-SLA query, whether filters combine, or what the unmentioned 'limit' parameter defaults to.

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 precise resource and condition ('candidacies that are OVERDUE on their stage SLA'), plus ordering ('worst first') and payload ('named'). It also explicitly carves out its niche against the funnel report's overdue count, so an agent can distinguish it from hr_funnel_report and hr_list_applications without opening a schema.

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 a clear usage frame: use this when a count tells you there is a problem and you need to know whose it is. That is a real when-to-use signal, but there is no explicit when-not or named alternative for a failed match (e.g. if you just want all applications, use hr_list_applications).

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