Merchant Catalog Acceptance

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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds meaningful behavior: deterministic, no network calls, no certification, pricing (0.05 USDC per job), and that invalid rows are reported as defects rather than rejected. It doesn't detail pagination or exact output shape, but no output schema exists and the deterministic/bounded-job details are useful.

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?

Three dense sentences: first states core function, second lists exclusions, third gives pricing. Front-loaded with the main verb and resource, no wasted words, every sentence adds distinct value.

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?

Complete for a deterministic validation tool: it defines what is checked, what is not checked, how bad rows are handled (reported as defects), and the cost. Given no output schema, a bit more detail about return structure could help, but the description already tells the agent what to expect (acceptance report) and the behavioral boundaries are clear.

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 low (50% across 2 params are described; the products array items are documented via per-property descriptions). The description summarizes validation scope but does not restate field-level constraints; the schema's per-field descriptions carry the bulk. The description adds the fact that numeric price values are reported as defects, which is extra context beyond the schema, but not enough to raise above baseline 3.

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 states a specific verb ('validates', 'flags', 'checks') on a specific resource ('supplied product catalog') and enumerates exact validations (GTIN checksums, price/currency/availability formats, duplicate SKU/GTIN, grouped-variant collisions). It clearly distinguishes itself from any certification/network-check tool by explicitly listing what it does NOT do.

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?

The description clearly states scope: 'Checks only the structured rows given in the request - no network calls, no brand or marketplace certification, no ISO 4217 currency list.' This gives strong when-to-use/not-use context. However, it doesn't explicitly name alternatives or say 'use this instead of X' because no sibling tools are provided.

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