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

Annotations already declare readOnlyHint/idempotentHint, and the description adds substantial behavioral context beyond that: exact SPDX IDs only, no glob patterns, unlisted licences default to WARN, concrete default policy values, data source (deps.dev), and a 1-hour cache. It also discloses what the tool returns (verdict, blocked_packages, warned_packages, policy applied). No contradiction 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 long but front-loaded with the core purpose, followed by parameters and behavioral constraints. Each sentence carries useful information, including the source/cache detail and the report_feedback fallback. The report_feedback sentence is somewhat generic and adds length, but it is actionable rather than filler.

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 output schema exists and annotations cover the safety profile, the description supplies everything else an agent needs to invoke the tool correctly: input format, size limit, required vs optional parameters, policy semantics, defaults, output fields, source, and an explicit alternative for CVE audits. No critical selection or invocation information is missing.

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%, providing a baseline of 3, but the description adds significant meaning beyond the schema: concrete examples (GPL-3.0, MIT), explicit default behavior for block/warn/allow, the 'No glob patterns — exact SPDX IDs only' constraint, and the default WARN handling for unlisted licences. This is exactly the kind of policy detail an agent needs to construct a valid policy argument.

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?

States a specific verb ('Audit'), a precise resource ('a CycloneDX or SPDX SBOM'), and a clear evaluation criterion ('against an SPDX licence policy') that returns a PASS/WARN/BLOCK verdict. It also distinguishes itself from a sibling by saying 'Use security_audit_sbom_vulnerabilities for CVE auditing instead.'

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?

Explicitly points to security_audit_sbom_vulnerabilities as the alternative for CVE auditing, and gives practical constraints for invocation: SBOM format, 500 KB max, policy structure, and default policy. It doesn't enumerate every related sibling (e.g., security_audit_licence_compatibility, security_audit_sbom_continuous), but the key routing guidance is present and unambiguous.

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