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

With no annotations, the description carries the behavioral burden. It discloses a non-obvious behavior: it rejects claims like 'optimal', 'verified', or 'feasible' when their evidence dependencies are incomplete. It does not state whether the graph is mutated or if this is purely read-only, but 'audit' implies non-mutating and the output schema covers return details.

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 compact and well-structured: the first sentence states purpose and timing, the second states the rejection behavior. Every sentence 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?

For a single-parameter audit tool, the description provides the core needed context: what it audits, when to invoke it, and what it rejects. The output schema covers return values. It lacks explicit side-effect disclosure and direct sibling differentiation, but these are minor given the low 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 0%, so the description must compensate. However, it only says 'for a task' and never explains what task_structure_id refers to, its format, or how to obtain it. The parameter title provides some meaning, but the description adds almost no semantic value beyond that.

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 uses a specific verb ('Audit'), identifies the resource ('the evidence graph for a task'), and states the operational context ('before issuing final answers'). It also distinguishes this from sibling tools like build_evidence_graph by making clear this is a verification/rejection step, not a construction step.

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 clearly states when to use the tool: before issuing final answers. It does not explicitly name alternatives or exclusions, but the context is strong enough that an agent can infer this is the pre-submission audit step rather than a graph-building or claim-evaluation tool.

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