Tool Capability Risk

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

Annotations declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description adds behavioral context beyond annotations: it connects to servers, calls tools/list, and classifies capabilities. No contradictions; the description enriches understanding without conflicting with annotations.

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 core purpose, followed by detailed method, parameters, and return value. It is relatively concise but structured, with no unnecessary sentences. A slightly shorter version could maintain clarity, but current form is well-organized.

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?

Given the tool's complexity (live introspection of multiple servers, risk scoring), the description covers inputs, outputs, and usage context comprehensively. It explains the discovery process, classification, returns format, and use case. Output schema exists, but description still provides enough 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 100%, so the schema already fully describes both parameters (config_path, timeout). The description restates the schema descriptions almost verbatim, adding no new semantic value. Hence baseline 3 applies.

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 clearly states the tool's purpose: live-introspection of MCP servers to score each tool's capability risk. It specifies the action (introspect, score), resource (MCP servers/tools), and distinct approach (connecting, classifying) which differentiates it from sibling scanning tools.

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 explicit guidance on when to use: 'assess the blast radius of MCP servers an agent can reach before granting or trusting their tools.' It does not explicitly mention alternatives, but the context makes it clear this is for dynamic risk assessment, contrasting with static analysis tools.

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