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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered structurally. The description does add real value beyond that: the five-candidate cap, absence of automatic selection, the required OAuth scope and EDIT_LISTINGS permission, and the failure modes (missing/foreign drafts, changed versions, unsupported identity fields). However, the consent requirement is stated twice with inconsistent wording ('OAuth store:listings:drafts:write consent' vs. 'separate store:listings:drafts:write consent and current EDIT_LISTINGS permission'), which undercuts confidence in the exact authorization contract.

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 purpose is front-loaded, but the body repeats itself heavily: no visual/paid inference appears twice, no automatic selection twice, read-only twice, and the consent requirement twice with different phrasing. Roughly half the sentences could be removed without losing information, and the duplication of the auth requirement is actively confusing rather than merely redundant.

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 three-parameter read-only inspection tool with an output schema and full annotation coverage, everything an agent needs is present: prerequisites, bounds, error conditions, and what the call does not do. The only shortfall is the conflicting consent statements, which a caller must reconcile before invoking.

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 the schema already documents limit, source_draft_id and expected_version in detail, making 3 the baseline. The description reinforces the meaning of the version guard ('saved version', stale-snapshot refusal) and the bounded limit ('up to five'), but adds no new syntax or format detail 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?

The opening sentence gives a specific verb and resource: 'Resolve saved native draft identity fields into up to five existing catalog candidates,' which an agent can distinguish from the plan/readiness and prepare/execute siblings. It never names those siblings explicitly, and the purpose is then restated three more times in slightly different words, so it is clear but not maximally sharp.

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?

'Inspect native catalog suggestions for one exact owned photo draft and saved version before choosing a catalog identity' states the pre-condition context for calling, and the description sets exclusions ('No visual or paid inference runs,' 'no new catalog rows'). It stops short of naming an alternative tool for the adjacent steps (e.g., draft readiness or plan inspection), so routing between the many draft siblings is still partly inferred.

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