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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context beyond that: a specific error-handling contract ('never raises a protocol error — it returns {"error": ...}') and the risk ranking hierarchy. It repeats the read-only/idempotent traits as reinforcement but adds genuine new information.

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 front-loaded with the purpose, then provides a compact example, usage note, and error behavior. It is slightly long but every section earns its place; no filler words or redundancies beyond the intentional restatement of safety traits.

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 moderately complex tool that ranks blast radius, the description covers purpose, risk model, input format via example, output structure, error handling, and a usage exclusion. Even with an output schema present, the description is self-sufficient and leaves no major gaps for an agent to guess.

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 100% (the 'tools' param is fully described). The description adds a concrete typical input example and the exact output structure, which helps the agent understand how the parameter is used in practice and what to expect in the response. This goes beyond the schema without contradicting it.

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 opens with a specific verb+resource combination ('Score the blast radius of every tool in a permission manifest'), and immediately differentiates itself from sibling audit_mcp_config by stating 'Not for the configuration that mounts them'. This leaves no ambiguity about the tool's function.

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?

It provides explicit usage guidance: 'Use on a permission manifest to rank tools by blast radius' and clearly excludes the alternative with 'Not for the configuration that mounts them (audit_mcp_config)'. This is exactly the kind of when/when-not guidance desired.

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