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

With no annotations, the description carries the full burden. It discloses the output artifacts (verdict, score, worst finding) and the accepted answer vocabulary, but says nothing about permissions, whether anything is persisted, cost/latency of the audit, or what happens when questions are left unanswered even though only budget_period_usd is required.

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?

Two tight sentences plus a link, with the purpose and the output shape front-loaded and no filler. The external link is placed at the end where it belongs, though its placement makes the invocation instructions feel incomplete.

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?

For a 19-parameter tool with no output schema, the description does explain the return artifacts and the required input. However, the substance of the 18 question parameters is undefined without fetching the protocol URL, so an agent cannot reason about the controls from the definition alone — a real completeness gap for a tool of this complexity.

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 100%, so baseline is 3. The description restates the yes/partial/no/unknown vocabulary already present in every parameter description and adds the meaning that the 18 named parameters are 'control questions,' but it does not explain what any individual question means — that is deferred to an external URL.

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?

Specific verb+resource: 'Audit the budget controls of an agent against thirteen loss patterns,' and it even names the return shape (verdict, score, worst finding). It implicitly separates itself from audit_coordination by scope, but never explicitly distinguishes itself from that or from check_spend, so it stops short of a 5.

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?

'Give budget_period_usd and answer the control questions with yes, partial, no or unknown' does tell the agent how to invoke it, and it points to a canonical question list. But it gives no when-to-use guidance versus siblings like check_spend or audit_coordination, and no indication of when this audit is or isn't appropriate.

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