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

Beyond the annotations (readOnlyHint=false, idempotentHint=false) it discloses concrete operational traits: the same 6-hour lock as the web button, 25 Pro operations cost, free-mode AUTH_REQUIRED response, and the estimate=true path returning a quote with allowed=false. This is exactly the context 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?

Front-loaded with the operation's effects, then usage, then cost, then example – a sensible order with no filler. It is dense and packs several clauses into one long sentence, which slightly hurts scannability but costs no accuracy.

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 mutation tool with an output schema present, the description supplies everything else an agent needs: trigger condition, alternative, locking/rate-limit behavior, pricing, and auth failure mode. The return values themselves are covered by the 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 coverage is 100%, so the baseline is 3. The description adds a concrete call example ({"id": "0000006865"}) and clarifies the estimate parameter's return semantics in free mode, which the schema's one-line description does not convey.

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 (odświeża) and resource (dane firmy), then enumerates exactly what refresh means: cache invalidation, reload including reports, indicator persistence, and returning changed fields. This clearly separates it from get_company, which only reads.

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?

"Użyj, gdy get_company zwraca dane wyraźnie nieaktualne... w innych wypadkach get_company wystarcza" gives an explicit trigger and an explicit default to the sibling. It additionally surfaces the 6-hour per-company lock and the cost, which an agent needs before choosing this over the cheap read.

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