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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the bar is lower. The description goes well beyond them, disclosing the statistical model (log-normal), the calibration sources (World Bank GNI per capita, Gini index, ILOSTAT with curated fallback), the 'null where none exists' handling, and the estimate-vs-payroll caveat.

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?

It is a single dense paragraph, but the methodology is front-loaded and every clause carries information (inputs, formula, outputs, caveat). No filler sentences, though the em-dash chain is heavy and would benefit from light structuring.

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?

An output schema exists so return values need not be explained, and annotations cover the safety profile; the description still fully specifies the model, sources, and outputs. It is essentially complete, missing only sibling-relative routing guidance.

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 the baseline is 3. The description still adds value: it explains that 'salary' locates a pay figure on the curve returning a percentile and out-earns %, and that 'percentile' returns the exact threshold wage — semantics that go beyond the terse schema field descriptions.

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 states a specific verb and resource ('Models a country's wage distribution', 'returns the ... bands') and enumerates the exact outputs (survival floor, minimum, p50, p75, p90, p99). It does not name or distinguish itself from close siblings like build_pay_range, localize_salary, or compare_occupation_pay, so an agent must infer the boundary.

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 closing clause 'Model estimates for benchmarking, not payroll data' signals the intended use case and warns against misuse. However, with ~50 sibling comparison tools, there is no explicit guidance on when to pick this over build_pay_range or localize_salary, nor when the optional salary/percentile paths apply instead.

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