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

The annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so 'Read-only' is confirmatory rather than new. The description nevertheless adds genuinely useful behaviour: the Austria-only scope gate, the clear error on a German id, and the shape of the payload (headline figures, percentiles within the UGB size class, nearest peers, plus a recency note). Remaining gaps are minor, e.g. how recency affects percentile validity or any rate limits.

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?

The purpose sentence is front-loaded and nothing is wasted, but the opening German sample question ('Beispiel: „Wo steht die Rauch Fruchtsäfte GmbH…“') is illustrative padding rather than operational information. Formatting artefacts — stray line breaks and indentation mid-sentence — slightly hurt scannability.

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 the description need not enumerate return values, yet it usefully summarises them and adds a recency caveat. With only two parameters, both fully explained, and the Austria scope constraint stated, an agent has everything needed to call this correctly on the first attempt.

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 0%, so the description carries the full burden and does: company_id is documented as 'AT:{fnr}' with bare FNR accepted and an Austria-only constraint with a stated failure mode, and n is documented as the count of nearest peers returned with an explicit default of 10. That is exactly the kind of format and validation detail the bare schema lacks.

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 opens with a specific verb and resource: 'Benchmark ONE company against its size-class cohort: headline metrics, percentile ranks and the nearest peers.' It also draws the boundary with the closest sibling, find_peers, so an agent can distinguish the two without inspecting either schema.

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?

It gives an explicit when (single-company benchmark against a size-class cohort) and an explicit alternative with the condition that selects it: 'For a cross-border meaning-based peer set use find_peers with cross_border=true.' It also names a hard exclusion — Austria only, because parsed financials are required — plus the failure mode for a German id.

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