brand_audit_get_report

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

Annotations already mark this as read-only, idempotent, and non-destructive, so the base requirement is met. The description adds valuable behavioral details beyond annotations: 'notReady' polling semantics, 'pdfUrl' being an authenticated download link requiring the same bearer credential, and 'pdfPending' for rendering state. This is meaningful supplementary information that helps the agent handle edge cases correctly.

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, each earning its place. The first establishes the core function, the second covers parameter behavior, and the third handles edge cases (notReady, pdfUrl, pdfPending). No filler, front-loaded with the primary action.

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 output schema exists Rodríguez, the description appropriately covers runtime behaviors not in the schema: polling (notReady), authentication for pdfUrl, rendering status (pdfPending). This is complete for a tool with two parameters and a rich output contract.

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?

Both parameters are 100% documented in the schema, so baseline is 3. The description enhances this by clarifying the semantic distinction: `target` yields per-target CheckResult, while omitting it yields audit-level aggregate. It also explains the meaning of the returned statuses (notReady, pdfUrl, pdfPending), adding value beyond the schema's bare field definitions.

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 opens with a specific verb+resource: 'Fetch the result JSON for a brand audit.' It clearly distinguishes this tool from siblings (e.g., brand_audit_status, brand_audit_batch_start) by focusing on retrieving results. The dual mode (per-target vs. aggregate) is explicit, removing ambiguity about what the tool returns.

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 when to use it (for completed audits) and explains the behavior of the optional `target` parameter eagerly. It implicitly signals not to use it for in-flight audits by mentioning 'notReady' polling. However, it does not explicitly name alternative tools (e.g., brand_audit_status) for checking status, so a bit more exclusivity would push it to 5.

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