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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower. The description nonetheless adds real domain semantics beyond annotations: the verdict logic (strength = best quartile, potential = worst quartile) and the default direction rule with named exceptions (leverage, days, costs). It does not mention peer-count minimums or output formatting, which are minor gaps.

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?

Compact but the opening sentence is a grammatical fragment and packs several clauses together, making the output description slightly hard to parse on first read. The two short follow-up sentences are efficient and front-loading is acceptable.

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 describing results, and it does so well by listing every returned element including the synthesized verdict. Missing pieces are the peer-count constraint (schema-only) and any error/degenerate-case behavior when peers lack a KPI.

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 only 33%, so the description must compensate — and it does meaningfully: 'Any KPI names work' clarifies the free-form KPI maps for target and peers, and 'Higher is better unless the KPI is leverage, days or costs, or better says otherwise' explains the default direction and the purpose of the `better` override. It doesn't address the 2-peer minimum, the 40-KPI cap, or the optional target name.

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 states a specific operation — benchmarking a target's KPIs against peers — and enumerates the outputs (quartiles, percentile, gap to median, verdict, strengths/potentials list). It is clearly distinguishable from siblings like valuation_multiples or valuation_scores by the peer-quartile framing, though it never names an alternative tool.

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 (compare one company's KPIs to a peer set) but there is no explicit statement of when to choose this over valuation_multiples/valuation_scores, nor prerequisites such as needing at least two peers. The 'Any KPI names work' and 'Free' notes give some helpful context but are not routing guidance.

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