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

With no annotations, the description carries the full behavioral burden. 'Return' implies a read, but the description says nothing about permissions, side effects, authentication, rate limits, or whether the tool is safe to call repeatedly.

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 or repetition. It is as concise as possible while still naming the operation and evidence domain.

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 describe return values, the definition remains incomplete for a five-parameter tool with many similar siblings. It does not explain when to use it, how to use the optional parameters, or how it differs from adjacent risk-contract tools.

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 has five optional parameters (decision, namespace, risk_tier, workflow_id, connector_id) with 0% schema description coverage. The description does not mention any of them, their expected values, or their filtering behavior, leaving parameter semantics entirely undocumented.

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 clear verb ('Return') and names the specific evidence type ('MCP tool annotation, trust, and session-combination risk evidence'). However, it offers no differentiation from closely named siblings such as recipes_mcp_risk_coverage_pack or recipes_mcp_tool_surface_drift_pack, leaving overlap ambiguity.

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?

There is no when-to-use guidance, no conditions, and no named alternatives or exclusions. The description only states what it returns, so an agent must infer its placement among the many sibling risk tools.

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