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

With no annotations, the description carries the full burden and does most of it: it discloses confidence-based branching (reuse frozen adapter, else plan/freeze/queue), first-call side effects (provisions and stores an adapter, may queue a review), the status vocabulary, and the auth/workspace prerequisites including a 403 refusal for sandbox keys. It stops short of saying who resolves a queued review or what the response contains beyond status.

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?

Five sentences, front-loaded with the core action and no filler. Each sentence adds a distinct fact (behavioral branching, status values, optional inputs, side effects, preconditions) despite one long compound clause.

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 four-parameter tool with nested schema, no output schema and no annotations, the description covers the operational essentials: side effects, confidence tiers, required credentials and the workspace-claim gotcha. It could go further by pointing to list_canonical_schemas for target ids and to decide_rosetta_review/list_rosetta_review for the queued-review path.

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 all four parameters; the description only restates them (samples improve the guess, merchant_id labels the audit trail). The phrase "up to a few more payloads" also understates the schema's maxItems of 20, which could mislead an agent into sending fewer samples than allowed.

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 and resource (onboard a merchant feed) and characterizes it as an end-to-end "one call" that fingerprints, reuses, plans, freezes or queues. This implicitly distinguishes it from the lower-level siblings like normalize_with_rosetta and translate_with_rosetta, but never names them.

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?

"Onboard a merchant feed with one call" suggests this is the orchestrated entry point, and "Pass samples... to improve the guess" gives one usage hint. However, there is no explicit when-to-use/when-not guidance against plan_rosetta_mapping, translate_with_rosetta, or normalize_with_rosetta, so the agent must infer the routing.

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