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

Beyond the annotations, the description adds substantial behavioral detail: OSV.dev as the vulnerability source, Redis persistence with 90-day TTL, input size limit of 500 KB, rate limit of 10/minute, no auth required, and action-specific return signals. This is exactly the kind of operational context that helps an agent predict side effects and constraints. The 'permanent' wording is slightly qualified by the TTL, but not contradictory.

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 dense and front-loaded with the core purpose, then proceeds through formats, persistence, limits, and use case. Most sentences earn their place. The final feedback-fallback sentence is boilerplate and not directly about the tool's behavior, which slightly reduces conciseness.

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?

With an output schema present and full parameter coverage, the description goes beyond what is required. It includes operational constraints, supported formats, persistence details, authentication requirements, rate limits, and a clear use case. The only minor omission is explicit deregister semantics, but the action enum and output schema likely cover that.

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 coverage is 100%, so the baseline is 3. The description adds value by clarifying how the parameters interact with the action lifecycle: 'Returns go_no_go signal on register; new_findings on check' and 'sbom Required for register action.' This gives the agent more insight into how to use each parameter than the schema 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 opens with 'Persistent SBOM watch' and immediately explains the lifecycle: 'Register once, check anytime for new CVEs affecting your dependency snapshot.' This clearly distinguishes it from one-shot vulnerability scanners like security_audit_sbom_vulnerabilities. It names the resource (SBOM watch), the actions, and the supported formats.

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 gives clear context: it is for DevSecOps teams monitoring production dependency exposure, and it emphasizes the persistent, repeated-use nature of the tool. However, it does not explicitly name an alternative for one-time SBOM scans or state when not to use this tool, so it stops short of full alternative routing.

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