Propose Merchant Center changes (applies nothing)

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

Adds substantial context beyond the annotations: the call writes nothing, it produces a proposal with a plain-English summary, feed-based products become overrides in Camberstack's supplemental data source and the merchant's feed is never edited, delete_product is undoable by re-creation, and ⚠ lines must be surfaced before approval. That is real behavioral disclosure for a mutation-adjacent tool whose annotations only say non-destructive/idempotent/open-world.

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?

Front-loaded with the essential fact (checks and proposes, changes nothing) and the required follow-up workflow before any enumeration. The 'Supported:' catalogue is information-dense but long and runs together in one paragraph; a short bulleted list would scan faster, though little is genuinely wasted.

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 2-parameter tool with full schema coverage, no output schema, and non-destructive annotations, the description covers purpose, safety, workflow, approval gating, reversibility, and the feed-vs-supplemental-data-source model. An agent has everything needed to call it and route the result correctly.

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 earns above that by explaining the semantics of the change types as a set — in particular that update_product only applies to Camberstack-created products while feed products must use set_product_attributes, and that feed changes are overrides layered on a supplemental source. It also gives motivating examples (price mismatch, missing GTIN, out-of-stock exclusion).

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 ('Checks Merchant Center product changes ... stores them as a proposal'), and immediately clarifies the crucial scope that nothing is applied. It distinguishes itself from the write-path siblings by naming apply_changes and undo_changes and by enumerating exactly which change types it accepts.

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?

Gives an explicit workflow — propose, show the summary, apply only after user approval via apply_changes, reverse with undo_changes — plus a stategic hint to also suggest fixing things in the feed or store. The one gap is that it never routes the agent against the generic propose_changes / propose_analytics_changes siblings; the reader must infer that merchant product changes belong here.

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