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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's added value is elsewhere: it discloses that the estimate is heuristic and derived from legal form, CZ-NACE and RŽP licences, and that ARES cannot show in-person payments or flat-tax status, which is why optional inputs override heuristics. It also describes the response payload in detail. Lacks anything on rate limits or failure modes when IČO is unknown/dissolved, but the disclosure of heuristics and data-source limits is substantive.

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 purpose, then a data-source caveat, then explicit Args and Returns blocks — a clean, predictable structure. It is fairly long, and the Args section partially duplicates enum definitions already in the schema, but no sentence is filler.

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?

No output schema exists, so the description carries return-value explanation itself and does so thoroughly (subject fields, verdict values, eet_off states, reasons, checklist, url, catalog_url). Combined with clear sibling routing and the heuristic/override caveat, an agent has everything needed to call and interpret this tool.

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 meaning beyond the schema: it explains why the optional answers exist (ARES gaps), states they override heuristics, and clarifies the enum semantics ('no' = not in the flat-rate regime). The example IČO format and 'spaces allowed' note are also useful beyond the schema's min/max length.

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 ('Look up a Czech business by IČO in the public ARES register') and the actual outcome ('estimate whether EET 2.0 applies, whether EET OFF is available, and what to do next'). The closing 'Don't use for' clauses name the sibling tools to use instead, so an agent can distinguish it from eet_classify_payment and eet_calculate_eet_off without opening any schema.

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?

Explicit routing: 'Don't use for: payment-type questions (use eet_classify_payment) or the EET OFF cost comparison (use eet_calculate_eet_off).' It also tells the agent when to supply optional answers ('pass the optional answers when you know them — they override the heuristics'), which is genuine conditional guidance.

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