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

Annotations already cover the read-only, idempotent, non-destructive profile, so the description's value is in the inclusion semantics it adds: expired credentials are included while missing/incomplete/inactive records are excluded, and totals are exact rather than page-scoped. It does not disclose ordering, default page size behavior, or response shape beyond that.

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 tight sentences, each doing distinct work: what it returns, what is in/out of scope, and which requests it is for. The primary scope statement is front-loaded with no filler.

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 correctly compensates by describing totals-plus-paginated-detail results, and it covers record inclusion boundaries. However, an agent can still not call it confidently: the 'state' filter is undefined and no ordering or pagination guidance is given for a 4-parameter tool.

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 implies locationIds ('by site/location') and pagination ('paginated'), but 'state' — a free-text 2-80 char string — is never mentioned and its meaning is unrecoverable from the schema; default limit/offset values and the 100/25000 caps are also unaddressed.

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 ('Report overdue credentials by site/location') plus the result shape (full-result totals with paginated employee/credential detail). Combined with 'No future renewal window' and 'not general gap counts', it is distinguishably different from list_expiring_credentials and get_training_gaps without opening either 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?

Says explicitly when to use it ('overdue-by-site requests') and when not ('not general gap counts'), and rules out future-window requests. It stops short of naming the concrete sibling to use instead, which is why it is not a 5.

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