buk_recurring_payroll

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

Annotations already declare readOnly/idempotent/open-world, and the description still adds genuine context: that increase_percent is a simulation rather than a mutation, and that the computed figure deliberately excludes non-base employer costs. What is missing is any hint of the result shape beyond 'by currency' (per-currency lines? per-employee rows?) and what happens when no wages exist for the date.

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?

Two tightly packed sentences with no filler; the core computation is front-loaded and the scoping caveat trails it as a qualifier. Every clause 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?

For a tool with no output schema and 17% schema coverage, the description covers the calculation and its main interpretive trap (base wages vs total cost) but not the return structure or the three scope-controlling parameters. Adequate to call correctly in the simple case, thin for anything involving descendants or area resolution.

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 only 17%, so the description must carry the parameter burden and does not. It clarifies as_of ('explicit date') and increase_percent ('simulate a percentage change'), but leaves area_ids, company_id, include_descendants (default true, materially changes scope) and the team/area_ids/company_id selection relationship completely unexplained in either place.

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 gives a specific verb and resource set: sum a team's contractual base wages as of an explicit date, grouped by currency, plus a percentage-change simulation. The clause 'This is a base-wage run-rate, not total employer cost' sharply separates it from cost-of-employment interpretations, though it never names the obvious sibling buk_team_payroll, so the boundary with that tool must be inferred.

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 rather than stated: the 'not total employer cost' caveat tells the agent what answer this tool gives, so an agent can infer it should pick this for run-rate/base-wage questions. There is no explicit 'use X instead when...' routing, no prerequisite or permission guidance, and no indication of when to prefer buk_team_payroll or buk_salary_history.

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