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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely non-redundant behavior: required auth scope, one bounded page per call with no automatic crawl, and an explicit allowlist of excluded sensitive fields (payroll, national IDs, contact/health info, free-text comments). It does not describe response shape or the maximum page bound beyond the schema.

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 carrying distinct payload: capability, auth requirement, pagination contract, and data-scope boundary. The permission and pagination constraints are front-loaded before the allowlist note.

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 should convey more about what the returned metadata contains beyond 'data plus opaque pagination tokens'. Auth, pagination, and sensitive-field exclusions are well covered, but with 8 parameters and low schema coverage the filter semantics remain unexplained, leaving the definition only minimally 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 coverage is only 38%: groupId, pageSize, and pageToken are documented in the schema, but employeeId, templateId, badgeNumber, startDateLte, and endDateGte have no description in either place. The description reinforces pageToken semantics ('never a URL to follow' appears only in schema) but never explains what the five filter parameters do, so it fails to compensate for the coverage gap.

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 specific verb+resource: reading a bounded page of agreement scheduling metadata (v3preview1). This is clearly a paged list operation, distinct from quinyx_get_agreement by implication (page, tokens), but the description never explicitly contrasts with the single-object sibling.

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 gives the prerequisite (hr:agreements:read) and explains the pagination usage pattern ('pass pageToken for another page, no automatic crawl'). However, it offers no guidance on when to use this vs quinyx_get_agreement or how the optional filters (employeeId, templateId, badgeNumber, date range) select which agreements to retrieve.

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