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

With readOnlyHint/idempotentHint/openWorldHint already covering the safety profile, the description adds real behavioral context: exactly one row per scope (pkd_full, pkd_division, pkd_section, region, country) and a non-obvious key convention where historically classified PKD scopes are version-prefixed ('v2007:62.01.Z'), with no prefix meaning PKD 2025. It does not say what happens when a company has no ranking or how to interpret rank values, so it stops short of 5.

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?

Three sentences, front-loaded with the core purpose, then the row/scope model with the version-prefix caveat, then the question pattern that selects this tool. The illustrative prefixes earn their space because the convention is otherwise unguessable from the schema.

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, yet the description discloses the return shape (one row per scope, enumerated scope keys) and the PKD version-key convention, which is the main thing an agent would otherwise misread. Combined with annotations covering safety and a fully documented schema, an agent has everything needed to call it correctly.

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 the baseline is 3, but the description goes beyond it by explaining what the scope_type values mean in practice and how the PKD-scope keys are version-tagged in the returned rows. It does not clarify identifier precedence (KRS vs NIP vs name) or behavior when all identifiers are omitted, which are the only remaining semantic gaps.

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 — a company's revenue rank positions — and names the three scopes (industry/PKD, region, country) plus the backing table company_financial_rankings. This is clearly distinguishable from siblings like get_financials or get_company, which return raw financials or entity data rather than rank positions.

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?

The closing sentence gives concrete usage framing: 'Use for questions like: where does company X rank in Poland / its industry / its region?' That is a clear positive trigger. It lacks any negative guidance (e.g., when to prefer get_financials over rankings) or prerequisites, which keeps it below 5.

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