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

Annotations already declare the write nature (readOnlyHint=false) and open-world scope, so the description focuses on what annotations cannot express: owner-only auth, the revision-roundtrip requirement from service_setup, and the explicit scope limit 'No payment or stock'. The word 'Replace' signals whole-object overwrite rather than a merge, which is important behavior an agent would otherwise miss, though it sits in mild tension with destructiveHint=false and the description never says whether omitted items are removed or what happens on a revision mismatch.

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?

Information is front-loaded with the highest-risk constraint (owners only, sign-in) followed by prerequisites and then field rules. The telegraphic fragments ('fixed/from need priceCents; confirm has null') are dense but each clause carries a distinct rule. The opening 'Replace only with products...' is awkward as a purpose statement and costs a moment of parsing.

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 single-parameter, deeply nested replacement tool with no output schema and no property descriptions, the definition covers the essentials: who may call it, what must be read first, the revision token, field-level pricing and variant rules, and what the tool does not handle. Remaining gaps (categories, fulfillment, revision-conflict behavior) are secondary to correct invocation.

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 0% on a deeply nested payload, so the description carries real weight and delivers: pricing enum rules ('fixed/from need priceCents; confirm has null'), variant semantics ('one-of options with their own price (null keeps the product price)'), and the meaning of photo and productUrl. It does not explain categories, fulfillment, enabled, available, or the maxItems caps, leaving nontrivial portions of the nested schema semantically bare.

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 description uses a clear verb ('Replace only with products, prices and options') and states the resource is the owner's product catalog, plus an explicit audience restriction ('Owners only'). It never names or contrasts against close siblings such as update_catalog or products, so an agent must infer which write path to take. Purpose is clear enough to call, but sibling differentiation is absent.

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?

Strong sequencing guidance: 'Read service_setup first and pass its products.revision' establishes a prerequisite call and a required value from it, and 'needs sign-in' sets the auth precondition. It also clarifies the downstream flow ('Customers order with request_order; the owner confirms in the conversation'), implicitly steering ordering away from this tool. There is no explicit when-not-to-use or exclusion against other update_* tools.

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