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

Annotations only declare readOnlyHint=true, and the description adds real behavioral context: the result shape (fixed version, CISA KEV, EPSS, disposition, workload/cluster counts), the note that it works with or without a BOM (per image.sbom_status), and the refusal behavior for unknown images. It could say more about pagination or rate limits, but the non-obvious failure mode is disclosed.

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?

Dense but front-loaded: the return shape leads, followed by scope/precondition, then the alternative tool. Every sentence carries information, though the long enumeration of returned fields in the first sentence is slightly heavy.

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?

There is no output schema, so the description correctly enumerates the returned columns and the refusal case, which is what an agent needs for a complex security query. Pagination and sorting behavior are delegated to the fully-documented input schema, leaving only minor gaps.

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 all seven parameters are already documented in the schema; baseline 3 applies. The description restates the image identifier semantics (digest or repository:tag) but adds no new detail about sort, order, search, or severity filtering beyond the schema.

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+resource ('List the vulnerabilities (CVEs) named on one image') and pins down the row grain (one row per CVE and installed package version). It clearly differentiates itself from get_security_finding and from the list_security_sbom_images / list_security_sbom_containers siblings used for image identification.

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 says when to use the alternative ('Use get_security_finding for one CVE's full detail'), how to select the image (digest or repository:tag from the inventory lists), and the precondition that an unseen image is refused. Nothing is left to inference.

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