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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behaviour, so the safety profile is covered. The description adds genuinely useful semantics beyond that: counts are applications rather than firms in the register, KRS-registered companies are excluded, and the index is defined with directional meaning (above 100 means the number of firms grows). What is missing is coverage period, publication lag, or units for the sums.

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?

Every clause carries real information, but they are crammed into a single run-on sentence with nested parentheses and a long enumeration, which hurts scanability. A short front-loaded statement of purpose followed by the caveats would serve an agent better without adding length.

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?

An output schema exists, so return-value explanation is not required, yet the description still clarifies the key semantic traps (applications vs. firms, KRS exclusion). Combined with the annotations, an agent has enough to call this correctly; only the data coverage window and the effect of the history parameter remain unspecified.

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% for the single optional parameter (history, default 12, max 60), so the schema carries the semantics. The description never mentions the history parameter or how it interacts with the reported aggregates (e.g., whether 'sums since January' and the 12-month index change with it). Baseline 3 applies.

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 and dataset: monthly CEIDG application counts (new registrations, closures, suspensions, resumptions) from the Polish Ministry of Development and Technology via dane.gov.pl. It even enumerates the metrics returned, so an agent knows exactly what a call yields. It does not, however, distinguish itself from siblings such as get_finwire_index or list_finwire_indices, even though it embeds the finwire_new_business_ratio index.

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?

Usage is only implied: an agent can infer this is the tool for questions about Polish sole-proprietorship formation and closure. There is no explicit when-to-use statement, no exclusions, and no routing to alternatives such as get_finwire_index, which appears to overlap on the ratio metric.

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