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

Annotations only declare readOnly=false and destructive=false; the description adds genuinely non-obvious behavior: drafts post nothing to the ledger, re-runs skip existing payslips (idempotent), and pay runs that finalise on their pay date are refused. These are the exact traits an agent needs before invoking, and none are derivable from the structured fields.

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 a distinct behavioral fact, with the core action front-loaded. No filler or redundancy.

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 mutation tool with no output schema, the description thoroughly covers creation semantics, ledger impact, idempotency and refusal conditions. The only real gap is the undocumented parameters, which is a notable but bounded omission.

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 0% and the description never explains the `id` or `employees` parameters. It even muddies the picture by saying payslips are created 'for each employee on its roster', leaving it unclear whether the optional `employees` array narrows the roster or is required to populate at all.

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 (fill/populate) and resource (pay run) plus the exact artifact created: a DRAFT payslip for each employee lacking one. This clearly distinguishes it from siblings like finalise_payslips and save_payslip 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?

Gives clear context for when to use it (populating a roster with drafts) and a when-not condition (auto-finalising pay runs are refused), plus idempotency guidance for repeat calls. It stops short of naming finalise_payslips as the follow-up alternative, so not a full 5.

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