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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds real value on top: a size warning for large pay runs and explicit disclosure that bank account numbers and tax/identity numbers are redacted. It stops short of describing pagination or how to handle oversized responses.

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 tightly packed sentences with zero filler: return shape first, then cost caveat, then redaction note, then the endpoint. Front-loaded and every sentence earns its place.

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 burden well by enumerating the returned field groups (earnings, deductions, tax, super, leave, gross/net, YTD) and the keying by employee. It leaves large-result handling and pagination unaddressed, which is the only meaningful gap.

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 100%, so all three parameters (including show_all_data) are already documented in the schema. The description adds no syntax or format detail about the parameters, so the baseline 3 applies.

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 ('Pay slip data for every employee in a pay run') and scopes it precisely with 'keyed by employee', which distinguishes it from the aggregate siblings like keypay_get_pay_run_summary and keypay_get_pay_run_totals. An agent can tell what it returns without opening the 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?

Usage is implied by the scope statement (per-employee detailed payslip data), and 'Large for big pay runs' warns about cost, but there is no explicit when-to-use guidance or routing against overlapping siblings such as get_pay_run_summary or get_pay_run_totals. Adequate but with a clear gap.

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