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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the data originates from a weekly NFOŚiGW summary (freshness cadence) and spans all editions plus the Modernisation Fund. It does not disclose pagination, latency, or whether the 'history' parameter changes the returned window — a notable omission for a time-series read.

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?

One long run-on sentence structured as a content inventory. It is correctly front-loaded with the programme name and source, but the middle third is a comma-spliced list that duplicates the output schema's payload description. It could be cut roughly in half without losing decision-relevant 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-optional-parameter read tool with an output schema present, the description supplies enough to identify the dataset, its source cadence, and its coverage. Since the output schema documents return values, the metric enumeration is redundant rather than necessary — the one real gap is the unexplained 'history' parameter.

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?

There is a single optional parameter whose schema entry is fully documented (100% coverage, default 8, range 0–120), so the schema carries the semantics. The description never mentions 'history' or explains whether it returns a series of past readings versus a single snapshot. Baseline 3 applies when the schema does the work.

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 names a specific resource — the Czyste Powietrze subsidy programme from the weekly NFOŚiGW summary — and enumerates the exact metrics contained (applications, contracts, paid subsidies, payout queue, payout rate). The closing 'National data only' implicitly distinguishes it from regional siblings such as get_regional_data. It never states a verb ('retrieve'/'get'), but the domain is unambiguous.

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?

'National data only' hints that get_regional_data covers the regional cut, and the named data source implies when this dataset is the right one. However, no explicit when-to-use rule, no named alternative, and no prerequisites are given. An agent must infer selection from the subject matter alone.

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