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

With no annotations provided, the description carries the full disclosure burden. It reveals a key behavior—rejecting claims based on incomplete evidence dependencies—but does not state whether the operation is read-only, has side effects, requires specific permissions, or what happens after rejection. 'Audit' implies inspection, but the rejection behavior is presented without clarifying its consequences.

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 is two sentences: the first front-loads the verb, resource, and timing, and the second provides concrete rejection examples. Every clause earns its place, and there is no redundant or filler content.

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?

The tool is simple (one required parameter) and has an output schema, so the description need not detail return values. However, it leaves notable gaps: the meaning of task_structure_id is not explained, side effects are not disclosed, and the relationship to build_evidence_graph is not mentioned. The description covers the core purpose but is incomplete for a fully informed agent.

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 must compensate for the lack of parameter documentation. It only says 'for a task', which loosely maps to task_structure_id, but does not explain what a task_structure_id is, how to obtain it, or how it relates to the evidence graph. This is insufficient compensation for an undocumented parameter.

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 action ('Audit'), the resource ('the evidence graph for a task'), and the timing ('before issuing final answers'). It also specifies concrete rejection behavior with examples ('optimal', 'verified', 'feasible'), which distinguishes it from siblings like build_evidence_graph and evaluate_claim_evidence.

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 gives a clear usage context: run this tool before issuing final answers, and reject claims with incomplete evidence dependencies. However, it does not explicitly name alternative tools or state when not to use it, so it stops short of the highest level of guidance.

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