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

Annotations already declare this as a safe, idempotent, closed-world read operation, covering the safety/mutation concerns. The description adds context about output content (percentiles, GUS data), which is useful, but doesn't mention retrieval constraints, caching, or data freshness/currency.

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 description mixes Polish and English, then partially repeats the same content in English, and lists output fields that overlap with the schema-defined parameters. It's moderately front-loaded but not perfectly tight; the bilingual restatement adds authoring overhead without new 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 single read tool with full schema coverage and no output schema, the description gives enough for expected return content but doesn't detail response shape, pagination, or edge cases. It's adequate but not rich, and its remaining gap is the exact output format since there's no output 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% – every parameter (city, contract, experience, occupation) is fully documented in the schema with enums, examples, and semantics. The description largely restates these (contract types, experience seniority) without adding format or syntax detail the schema lacks, so baseline 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 description clearly states it returns salary statistics (median, quartiles, typical ranges) for an occupation in Poland or a city, and mentions supporting breakdowns by contract type and experience. It's a specific verb+resource, but unlike the sibling-routing example it doesn't contrast itself with compare_occupations or get_rankings, which could also involve salary data.

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 (need an occupation identifier, optionally a city/contract/experience) but there's no explicit when-to-use-vs-alternatives guidance. The description doesn't distinguish this from compare_occupations, which likely does salary comparison, leaving the agent to infer the boundary.

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