Blast Radius Analysis

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

Annotations already indicate read-only, non-destructive, idempotent, and open-world behavior. The description adds valuable context: it returns 'found=false' if the CVE is not found, and lists the JSON fields (risk_score, affected_servers, etc.). This goes beyond annotations without contradiction.

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 main purpose and then provides details on scanning and return values. It is reasonably concise, though the return format could be integrated into the first paragraph to be even tighter.

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 one parameter and an output schema (not shown but mentioned), the description is highly complete. It covers how the CVE is used, what scanning does, and the structure of the return value including error handling. No gaps remain.

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 single parameter 'cve_id' is well-described in the schema. The description adds concrete examples like 'CVE-2024-1234' or 'GHSA-xxxx', which improves usability. With 100% schema coverage, baseline is 3, but the extra examples justify a 4.

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 that the tool looks up the blast radius of a specific CVE across AI agent setups, scanning MCP configurations and returning the full attack chain. This distinguishes it from sibling tools like 'scan' or 'inventory', which are more general.

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 explains that the tool scans local MCP configurations for a given CVE and returns the attack chain, implying its use is for security impact analysis. While it does not explicitly state when not to use it or list alternatives, the context is clear given the sibling tools.

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