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

With no annotations, the description carries the full burden. It discloses the conditional behavior based on idempotency_key, explicitly states that no presigned URLs or storage keys are returned, and notes that 'Provider presigned URLs and storage keys are never returned' as a hard constraint. It also advises to 'Trust the returned upload_attempt and reconciled fields,' hinting at the response structure. However, it does not explicitly state whether this operation creates or modifies any records, though it implies work is done in the keyed case. It is highly transparent but leaves a minor gap on side effects.

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 long but dense and well-organized: the first paragraph establishes purpose and conditional behavior, the second lists parameters with constraints, and the third provides an example. Every sentence adds value, and the critical upgrade_required behavior is front-loaded. There is no fluff or repetition.

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 tool's complexity (conditional behavior, 7 parameters, no output schema, no annotations), the description covers purpose, behavior, parameter constraints, and an example. It explains the upgrade path and what is never returned, but it does not describe the full success response structure (only hints at upload_attempt and reconciled fields). Since there is no output schema, a bit more detail on the response shape would improve completeness, but the description is largely sufficient for 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%, so the description is the only source for parameter meaning. It enumerates all required parameters with constraints (content_type allowed values, file_size ≤500MB, file_hash sha256 hex) and explains optional ones (idempotency_key for retries/reconciliation, upload_attempt increment only on retry, folder_id UUID). The example further clarifies the expected payload. This fully compensates for the schema's lack of descriptions.

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 role as a 'Compatibility entrypoint' for requesting creative uploads, with an explicit conditional behavior: calls without an idempotency key return upgrade_required and recommend creatives_request_upload_v2, while calls with a key use the redacted v2 proxy contract. This distinguishes it from siblings like creatives_request_upload_v2 and creatives_confirm_upload, making its purpose unambiguous.

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 explicitly explains when to use this tool versus the alternative: it tells the agent that without a stable idempotency_key, it will return upgrade_required and recommends v2, implying that v2 is the preferred modern entrypoint. It also clarifies that presigned URLs and storage keys are never returned, setting expectations for what this tool does and does not provide. This is explicit routing guidance.

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