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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered. The description adds genuinely useful behavior: the register has been live since July 2026, it includes sub-threshold contracts, it is keyed by NIP, and it details what is returned. That is real added value beyond the annotations.

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-loads what the tool does, then the returned payload, then the register context and identification keys. Information-dense but every clause earns its place and there is no 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?

With no output schema, the description carries the burden of explaining returns and does so (count, total value, top buyers, 50 most recent with date/subject/value/buyer/link). It omits pagination or whether results can exceed the 50 shown, which is a minor gap for a lookup 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% and the schema already marks NIP as preferred for CRU. The description reinforces 'keyed by NIP' and 'identify company by name, KRS, or NIP', adding only marginal meaning over the structured fields. Baseline 3 is appropriate.

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 and pins the exact data source: contracts from Poland's CRU JSFP register where the company is the public-sector contractor. It also enumerates the returned data (count, total value, buyers, recent contracts). It stops short of distinguishing itself from similarly named siblings like get_company_public_tenders, so an agent must infer that 'contracts' vs 'tenders' is the difference.

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 implied by the description ('covers contracts below tender thresholds too' hints when this is useful), but no explicit when-to-use, when-not, or alternative tool is named despite a crowded family of get_company_* contract/tender siblings. The agent gets context but no routing guidance.

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