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

Annotations already cover read-only/idempotent safety, so the bar is lower; the description nonetheless adds meaningful behavior: output is an 80% interval, a single number appears only at high confidence, and the value matches the building card, map and report. The 'not a formal valuation' caveat adds important expectation-setting.

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 core purpose and the input rule are front-loaded, but the description is a dense, slash-separated bilingual run-on that mixes output shape, input rules and disclaimers into one block, making it slower to parse than necessary.

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 no output schema, the description correctly compensates by describing the return values (interval, unit, confidence, justification sentence). For an 8-parameter, all-optional estimation tool the coverage is nearly sufficient; only the sibling-choice guidance is thin.

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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond it: the either/or relationship between budynek, adres and lat/lon, and the behavioral consequence of omitting metraz. This helps the agent choose inputs rather than just format them.

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+resource: a statistical price estimate for an apartment, with the output shape (80% interval, PLN/m², confidence, justification). It implicitly separates itself from szacunek_domu/szacunek_dzialki by naming the resource, but never explicitly contrasts with those 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?

Tells the agent what to supply (building number from the report, address, or coordinates plus floor area) and clarifies the fallback when only a building is given (typical second-hand flat). It also flags the 'not a formal valuation' limitation and the pokaz_liczbe condition, though it does not name when to prefer a sibling tool.

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