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

Annotations already provide readOnlyHint, idempotentHint, and openWorldHint. The description adds value by detailing the return format (status enum, progress 'N/M', per-target statuses) and the owner-scoping behavior (notFound for other principals). It also implies polling semantics. No contradictions.

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?

Two sentences that efficiently convey the core purpose, return types, and a key constraint. Every word adds value with no redundancy or fluff.

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 status polling tool, the description covers the essential behavior: status codes, progress reporting, per-target details, scoping, and source of auditId. Combined with the output schema (present), the agent has sufficient information to use and interpret results 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% with a clear description for auditId. The description adds semantic context: the parameter must come from brand_audit_batch_start and that owner-scoping means other-owned IDs return notFound. This goes beyond the schema's basic description.

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 polls the status of an enqueued brand audit, specifying return fields (audit-level status, progress, per-target statuses). It distinguishes from siblings like brand_audit_batch_start and brand_audit_get_report by focusing on status polling, and adds owner-scoping constraints.

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 implies usage after brand_audit_batch_start (auditId from there) and notes owner-scoping behavior. It clarifies that audit IDs belonging to others surface as notFound. While it does not explicitly exclude alternatives or provide when-not guidance, the use case is clear and contextually sufficient given sibling tool names.

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