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

Annotations indicate readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds significant behavioral context: it explains the multi-stage workflow (Stage 1, Stage 2, Stage 3), the need for reviewer sign-off, the requirement for a confirmed seller email, and that questions are returned with keys. It also notes that the first response is preliminary and can be shown to the seller immediately. This goes beyond the annotations, which only say it's idempotent and non-destructive. The description does not contradict annotations; it complements them.

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 description is moderately long but well-structured. It front-loads the core purpose and immediate value ('the first response already contains preliminary requirements...'). It then explains the workflow and key behaviors. Every sentence adds information: the next_action instruction, the question key handling, the email requirement, and language support. It's not overly verbose, but it could be slightly more concise by trimming redundant phrases like 'execute it exactly as returned' which is somewhat redundant with 'follow next_action exactly'. Still, it's efficient and well-organized.

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?

Given the complexity of the tool (5 parameters, nested objects, output schema, multi-stage workflow), the description is remarkably complete. It covers the input format, the output expectations, the workflow stages, the action parameter semantics, the handling of questions, the email requirement, and language support. The output schema exists, so return values are not described in the description, which is appropriate. The description provides all necessary context for an agent to use the tool correctly, including the exact next_action values and their meanings.

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 parameters. The description adds value by explaining the action parameter's workflow semantics (e.g., 'start_stage_2 assesses evidence after the Stage 1 product profile is ready') and the meaning of next_action. It also clarifies that message should not repeat information already supplied, and that language is inferred when omitted. This goes beyond the schema's basic descriptions, providing operational context. However, it doesn't detail the answers structure beyond what the schema says, but the schema is already rich.

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 clearly states the tool's purpose: checking what a product needs to be sold into specific markets (EU, UK, US, Australia). It specifies the input (plain-language product description) and the output (preliminary requirements and evidence checklist). It distinguishes itself from siblings by focusing on market-access requirements across multiple regions, whereas siblings like check_amazon_compliance_request or check_us_import_certification are more specific. The verb 'check' and resource 'product market-access' are precise.

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 provides explicit guidance on when to use the tool: to get market-access requirements for a product. It also explains the workflow: send a description, receive preliminary requirements, then follow the next_action exactly. It mentions alternatives implicitly by naming sibling tools that are more specific (e.g., check_us_import_certification for US import certification), but the description itself doesn't explicitly say 'use this instead of X'. However, it does give clear context on the multi-step process and how to handle returned questions, which is strong usage guidance.

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