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

'Return' communicates a non-mutating retrieval operation, which is a useful behavioral cue, but nothing is disclosed about data sources, freshness, authentication, or failure behavior. Since annotations are absent, the description carries the transparency burden and only partially satisfies it; the existence of an output schema helps offset the lack of return-shape detail.

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 front-loaded sentence with no filler, making it structurally concise and easy to scan. The brevity is achieved at the cost of missing usage and parameter context, but that is more appropriately penalized in other dimensions.

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 tool with five filter parameters and a large sibling set of risk, trust, and contract tools, the one-sentence description leaves meaningful gaps: no matching semantics, no alternatives, and no preconditions or scope. The output schema may document return values, but it does not clarify input semantics or when this evidence contract is the right choice.

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?

The schema lists five optional nullable strings, but the description gives no mapping between parameters such as decision, risk_tier, workflow_id, or connector_id and how they filter or shape the returned evidence. With 0% schema description coverage, the description does not compensate, leaving meaning to be inferred from parameter 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 uses a specific verb ('Return') and names the output domain ('MCP tool annotation, trust, and session-combination risk evidence'), which clarifies the core purpose. However, it does not contrast with semantically close siblings such as recipes_mcp_risk_coverage_pack or recipes_secure_context_evidence_contract, so some differentiation is left to the agent.

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?

No guidance is provided about when to call this tool versus alternatives like recipes_mcp_risk_coverage_pack, recipes_agentic_telemetry_contract, or recipes_secure_context_evidence_contract. The description states only what is returned, not when it should be used or when a different tool would be more appropriate.

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