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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real behavior beyond them: proration for LOP days or mid-month joining, full payment for bonus/reimbursements, the exact computed outputs (gross, total deductions, net pay, net pay in words, download links), and hard limits (no statutory PF/ESI/PT/TDS computation, no PAN/UAN/bank numbers). These are substantive operational facts an agent cannot infer from 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?

The definition is front-loaded with the trigger and the input-shaping rule, then behavior, then exclusions — a sensible order. It is a single dense paragraph covering a lot of ground with little waste, though it is long enough that the exclusions and no-statutory-computation caveat could be separated for easier scanning.

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 24 optional parameters, an output schema, and rich annotations, the description covers purpose, computation rules, output summary, and hard limits well. The remaining gap is that with zero required parameters it never states the minimum viable input (e.g. what happens if earnings is omitted or only a name is supplied), and defaults like month defaulting to last month are left to the schema.

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 every one of the 24 parameters is already documented in the schema, and the description largely restates the earnings/deductions item shape ({name, amount}, percent/of) rather than adding new semantics. The one useful addition beyond the schema is framing the pasted text list as an acceptable fallback, but that is also present in the schema's own descriptions, so the baseline of 3 is appropriate.

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 first sentence gives a specific verb (generate), resource (salary slip/payslip, India format), output artifacts (PDF and Excel), and input source (earnings and deductions the user gives). The closing sentence explicitly carves out what the tool is not for (salary negotiation, CTC planning, tax calculation), so an agent can distinguish it even without siblings.

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?

It states the trigger condition ("Use this when the user wants a salary slip") and explicit exclusions ("Do not use for salary negotiation, CTC planning or tax calculation"), which is the when-not half most descriptions omit. It also tells the agent how to shape input, including a low-effort fallback (a pasted name/amount list), which is actionable routing guidance.

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