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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description adds that approval is deliberately out of scope and that diagnostics explain unpayable shifts (no grade, no rule, no plan). That meaningfully exceeds what the annotations say. It does not mention pagination behavior for listing periods, which is the main remaining behavioral gap.

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?

The returned-content inventory is front-loaded, followed by use-case questions, then the read-only caveat. Dense but nearly every clause carries information. The em-dash aside about the named period is slightly tangled but not wasteful.

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 read-only summary tool with two optional parameters and no output schema, the description fully characterizes the response shape in both listing and detail modes, including diagnostics. Only the limit parameter's behavior is left unaddressed, a minor omission against an otherwise complete picture.

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 50%: period_start is self-describing ('OOO to omit to list periods'), and the description reinforces the two modes ('for one named period' vs. listing). The limit parameter — capped at 24 — is undocumented in both schema and description, so the agent gets no guidance on how many periods are returned by default or why 24 is the ceiling.

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 resource (payroll periods) and enumerates exactly what is returned: dates, status, total amount, staff count, and — for a named period — per-person base/commission/bonus/extras plus diagnostics. This is far more than a restatement of the name. It does not distinguish itself from the close sibling fin_payroll_summary, leaving the retail-vs-finance split to inference.

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 concrete triggering questions ('what does this period come to', 'who is missing from it', 'why is someone's pay lower than expected') that map directly to the two call modes. It also states an explicit exclusion — approving a period is not available here — which prevents a misuse. It stops short of naming an alternative tool when the agent actually needs approval or finance-level data.

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