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

With no annotations supplied, the description carries full responsibility for disclosing side effects and behavior, but it only lists output content. It does not indicate whether the operation is read-only, whether it requires prior evidence compilation, or what happens if evidence is incomplete. This leaves important behavioral traits unstated.

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 a single sentence that efficiently packs the core action and output categories without extraneous words. It is front-loaded with the main verb and object. The dense list is acceptable, though it could benefit from breaking the output items into structured form.

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?

Although an output schema exists and reduces the need to explain return values, the tool still lacks guidance on parameter meaning, usage context, and prerequisites. With no annotations and no alternative routing, an agent cannot fully determine when and how to invoke this tool. The description covers only the content of the result, not the surrounding operational context.

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 is the only place to explain target_id and task_structure_id. It never mentions either parameter or how they influence the compiled result. The agent is left without any guidance on what values to supply or why task_structure_id is required.

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 states a specific action, 'Compile a final evidence result,' and enumerates the exact content categories it includes, making the tool's purpose clear. This resource is distinct from siblings like build_evidence_graph or audit_evidence_graph, though the description does not explicitly contrast them. The verb 'compile' vs the tool name 'get' introduces minor ambiguity about whether it retrieves or constructs the result.

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 information about when to use this tool instead of related evidence tools, such as cognitive_audit_evidence_graph or cognitive_build_evidence_graph. There are no stated prerequisites, use cases, or exclusions. An agent must rely on the tool name and implicit context to decide when this tool is appropriate.

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