Draft backport patch

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

With no annotations, the description carries the full burden and mostly does: it discloses it writes only into a staging directory, explicitly never mutates the running system, and returns a conflict report plus evidence chain. Missing are prerequisites, overwrite behavior for an existing staging dir, and any permission requirements, keeping it from a 5.

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?

Three short, front-loaded sentences with no padding: purpose, behavior, return values in that order. The opaque rule identifiers (R4, R1/R5) cost a little clarity without adding length, but the structure is sound.

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 mutation tool with no annotations and no output schema, the description usefully names the return artifacts, which compensates for the absent output schema. It still omits prerequisites (e.g., whether find_patches/scan_system must run first) and what happens with unresolved conflicts, leaving gaps for a write-capable tool.

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 50%: outputDir and targetBranch are documented in the schema, while cveId and upstreamSha are bare. The description's "commit <sha> upstream" hints at what upstreamSha means and the staging wording reinforces outputDir, but cveId and targetBranch semantics are untouched, so it adds only marginal meaning.

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 (draft) plus resource (kernel-rule-compliant backport) and the destination (staging directory), with concrete outputs named (conflict report, evidence chain). It is unmistakably distinct from the query/dependency siblings, but never names or contrasts any sibling explicitly, so it stops short of a 5.

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?

"Never applies to running system (Rule R1/R5)" is a genuine exclusion, telling the agent this cannot be used to activate changes. However there is no positive when-to-use guidance and no routing relative to find_patches or scan_system, which an agent would need to know whether to run this first or after patch discovery.

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