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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering safety and world-access expectations. The description adds that inputs are validated server-side and the deliverable includes score, roadmap, findings, and premium savings, offering some output context. However, it does not disclose details about async behavior (despite the async parameter), cost/payment implications, or any potential side effects beyond the read-only claim, leaving moderate 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?

The description contains three sentences, but the first sentence includes promotional fluff ('Gapup agent-payable C-suite expertise (RISK)') that does not aid functional understanding. The reference case is somewhat useful for illustrating output, but overall the text is not tightly front-loaded and includes non-essential marketing language.

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?

This is a complex tool with multiple required nested objects and no output schema, yet the description does not fully explain the structure of the deliverable or how to populate the input fields. It mentions a reference case with output metrics, but omits details about async handling, field validation requirements, or output format. Given the lack of an output schema, the description leaves significant gaps for correct invocation.

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 only 20% (only the async parameter has a description), yet the tool description does not compensate. It mentions 'documented case fields' but does not explain the nested objects (company, techStack, currentPosture) or the meaning of their subfields, such as dataTypes or hasSOC2orISO27001. The reference case gives an example but not field-level semantics, leaving the agent to infer parameter meaning from names alone.

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 clearly identifies the tool as a cyber risk auditor ('Auditeur de risque cyber') and states it 'Returns a structured, audited deliverable,' with a reference case showing outputs like a score, roadmap, and findings. However, it uses a noun phrase rather than a direct verb (e.g., 'audits') and does not explicitly distinguish from sibling security audit tools, as the expected function is implied rather than explicitly stated.

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 description provides no guidance on when to use this tool versus alternatives. There is no mention of preferred use cases, exclusions, or relationships to sibling tools like audit_pre_flight or pentest_scope_estimator. The only related statement is 'send the documented case fields,' which is an instruction for input handling, not a usage guideline.

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