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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds value by stating the return contents (leak checklist, extract required, fixed fee) and by framing the answer as what the audit 'would look for,' signalling this is explanatory rather than a live computation against company data. It stops short of saying explicitly that responses are industry-templated rather than evidence-based.

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, each doing distinct work: what it explains, when to reach for it, and what comes back. The trigger sentence is front-loaded in the middle position and there is no filler or repetition of the title.

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, no required parameters, and only a read-only lookup to perform, the description is nearly complete: it covers triggers, scope, and expected return. The one gap is that it never states whether output is tailored to the supplied industry/symptom or is a generic audit template, which matters for an agent deciding whether the call is worth making.

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% with four optional parameters, each already described with examples (symptom phrasings, industry list, ERP note, revenue for sizing). The description only implies that these shape the answer by referring to 'a given company' and 'typical magnitude'; it adds no syntax, default, or interaction guidance beyond the schema, so the 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 gives a specific verb+resource pair — 'Explain what Bramvia's Profit Leak Audit would look for in a given company' — and names the concrete outputs (leak checklist, data extract, fixed fee). It is clearly a marketing/advisory explainer rather than an assessment tool, but it does not explicitly contrast itself with the nearby sibling assess_erp_health, which could also be reached for by 'what is wrong with their business'.

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?

Explicit trigger language is provided: 'Use when someone asks where their margin is going, what is wrong with their business, or how to find hidden costs.' That covers the when-to-use case well, but there are no exclusions or named alternatives, so an agent must infer that estimate_bridge_to_cloud_savings or assess_erp_health are the different tools for quantified diagnosis.

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