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

Annotations already cover the safety profile (readOnlyHint, openWorldHint, non-destructive). The description adds genuinely useful operational context beyond that: the 5-minute polling cadence, the fact that this is reachability rather than transaction-level health, and where official notices live. It doesn't discuss rate limits, caching/staleness of the 24h/7d/30d windows, or error behavior.

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 core answer, then the differentiator, then the Args block. The long comma-spliced return-value list in sentence one is dense, and the Args section duplicates schema content, but there is little outright waste.

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 compensates by enumerating the returned signals (status values, last check, latency, uptime windows, recent outages) and disambiguating what the status actually measures. Nothing an agent needs to call and interpret this tool correctly is missing.

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% and the enum for response_format is fully documented in the schema, so the schema does the heavy lifting. The description's Args line merely restates 'markdown'|'json' without adding semantics. Baseline 3 is appropriate for a single fully-documented parameter.

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?

Specific verb + resource: 'Return the current availability of the Finanční správa EET 2.0 interface' with named environments (production trzbyeet.gov.cz, Playground) and the measurement source (EvidujZdarma, every 5 minutes). It enumerates exactly what is returned (status, last check, latency, uptime windows, recent outages), which cleanly separates it from siblings like eet_classify_payment or eet_get_facts.

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?

Gives clear context for use and an explicit boundary: 'It measures reachability of the server, not the processing of individual sales,' plus a pointer to the authoritative alternative ('Official outage notices are published on eet.gov.cz'). It stops short of naming a sibling tool or stating when-not-to-call in tool-routing terms, so it's strong but not a 5.

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