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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond them, disclosing the dry-run gate, the confirm-required reason token, batch atomicity ('refuses the whole batch'), and side-effect boundaries (no emails, no returns). No auth/permission detail, but the behavioral profile is unusually rich.

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?

Front-loaded with purpose, then scope negatives, the confirm workflow, and refusal conditions in a logical order with no filler. A couple of clauses are dense and run-on ('Without confirm true it changes nothing and answers reason confirm-required with what it would post'), but every sentence adds actionable information.

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 2-parameter mutation tool with no output schema and minimal annotations, the description supplies the workflow, prerequisite safety gate, failure modes, and side-effect scope. An agent has everything it needs to call this correctly, including the partial-response hint about `reason: confirm-required`.

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% (only `confirm` is documented in-schema), so the description carries `ids` by explaining its batch semantics and that a missing or another business's id refuses the whole batch. It also reinforces the confirm gate beyond the schema text. It does not specify the id string format, so it falls just short of full compensation.

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+resource (finalise payslips) and the concrete effect ('each posts its journal to the books'), which distinguishes it from siblings like save_payslip, get_payslip, delete_payslips, and populate_payrun. It also scopes what it does NOT do ('Sends no email and files no returns').

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 an explicit two-step workflow: without confirm=true nothing changes and the tool answers with what it would post; the agent must ask the user, then re-call with confirm=true. Refusal conditions (locked period, self-finalising pay run, missing/foreign id) tell the agent exactly when the call will fail and why.

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