av_explain_finding

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

With no annotations the description carries the full burden, and it does disclose non-obvious behavior: the shared snapshot/index basis, session mode being read-only against the current round only, hard-error rather than silent full rescan, and repo being mandatory. It still omits what the returned evidence/fix structure looks like or permission requirements.

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 tight sentences that front-load the core action before the snapshot/session caveats and the required-parameter note. No padding, though the repo reminder is somewhat redundant with the schema.

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 finding-explanation tool with no output schema, the description covers inputs, snapshot semantics, and failure behavior adequately. A brief note on what the explanation contains would close the remaining gap.

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 reinforces that repo must be an absolute workspace path and that from=session restricts the lookup, but both points are already stated in the schema, adding little beyond it.

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 (解释) and resource (某条 finding), plus what it returns conceptually — 结构化边证据与修复建议. It names av_check_layering to establish lineage, but does not sharply contrast itself with the other siblings (av_session_report, av_status), so sibling differentiation is partial.

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?

Explains default behavior (same snapshot/index as av_check_layering, excluding inventory) and when the from=session path applies, including that a missing report errors instead of falling back to a full rescan. It does not explicitly tell the agent when to prefer this over av_check_layering or av_session_report.

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