Decide Reconciliation Candidate

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses version bumping on apply, no new version on reject, idempotency on the pair, org-scoped visibility of rejections, the heuristic-tier refusal gate requiring confirm_heuristic, server re-validation with 400 on stale models, and 503 when composition is unavailable. It even names what record gets dropped when the pair stops matching.

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 mutating and input-tool facts are front-loaded, and the three decisions are cleanly bulleted so an agent can scan to its branch. It is dense and somewhat long, but almost every clause adds operational detail (refusal gate, error codes, return shape) 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?

For an 8-parameter mutating tool with no annotations and no schema descriptions, this is close to complete: preconditions, decision semantics, error codes, heuristic confirmation, version effects, and return payloads are all covered. An output schema exists, yet the description still names the key response fields, so an agent knows what it gets back.

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 0% across 8 parameters, and the description compensates for most of them: kind enumerates assets/attackers/components, own_qid/inherited_qid are documented with concrete example formats ('child:A1'), decision values are explained semantically, and confirm_heuristic and rejection_id are given meaning and provenance. model_id and server_version are required but their roles are only implied by the 400 re-validation note, not stated explicitly.

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?

Opens with a specific verb+resource ('Decide a reconciliation candidate') and immediately ties it to the sibling that produces its input, list_reconciliation_candidates. The 'Mutating.' flag plus the per-decision breakdown make it unmistakable against read-only siblings like list_reconciliation_candidates.

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?

Each decision value is given a clear condition: 'apply' when the descendant's own entity IS the inherited one, 'reject' for 'these are NOT duplicates' at org scope, 'unreject' to pull a rejection_id from list_reconciliation_candidates(disposition="rejected"). It also flags recovering from a 400 by refreshing the list. It does not compare against adjacent decision tools such as decide_inventory_pair or reconcile_model, which keeps it from a 5.

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