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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=true and destructiveHint=false; the description adds substantial context beyond them: it creates a calculation job rather than a record, identical scenarios from the same caller resume the same job for 29 minutes (concretizing the idempotency window), and the initial response contains no confirmed amount. It also bounds the result semantics (totals cover returned components only; fees, deposits and unlisted benefits are not confirmed), which is exactly the kind of disclosure annotations cannot carry.

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?

Six tightly packed sentences, front-loaded with the purpose and the anonymity constraint, each carrying distinct information about behavior or follow-up. It is long but not padded; slight compression of the totals-disclaimer clause would tighten it further.

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 an asynchronous, open-world job-creating tool, the description covers the critical gaps an agent needs: anonymity rules, async polling contract, idempotency window, and result-scope caveats, and an output schema exists so return structure needn't be explained. The only residual gap is the optional region_code/tax_year semantics.

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 13%, so the description must compensate, and it partially does by naming the required dimensions: country, currency, period and gross/net basis. However, it says nothing about region_code (a large enum that plausibly changes the calculation), tax_year, or language, leaving four of eight parameters with no narrative meaning beyond the schema types.

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: submit an anonymous hypothetical salary scenario to the PIO website calculator. It immediately clarifies what the operation is not (never an employee, bill or payment), which removes the most likely ambiguity for an agent reading the name.

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?

Explicitly excludes a whole class of inputs (do not use employee records or personal/company information) and routes the agent to the sibling tool get_employer_cost_estimate for polling with estimate_id after retryAfterSeconds. When-to-use, when-not-to-use, and the alternative are all spelled out.

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