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

With no annotations, the description fully discloses critical behavioral traits: the tool is credential-free, enforces various limits (rate, concurrency, size, type, prefix), and returns either upload_endpoint or dedup_success. It also warns about what it never returns, preventing misuses. This is exceptional transparency beyond typical descriptions.

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 dense but organized: first the core function, then security/constraints, then required/optional parameters, then an example. Every sentence adds value, and the example is compact. It is front-loaded with the most critical information (what it returns and never returns).

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 (7 params, no output schema), the description covers all essential aspects: idempotency, endpoint, authentication, constraints, and an example call. It even details the return behavior (upload_endpoint vs dedup_success). The example clarifies usage. It is complete for an agent to call 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 0%, so the description must compensate. It does by listing required parameters (filename, content_type, file_size, file_hash, idempotency_key) with constraints (1..500MB, lowercase 64-hex, etc.) and optional ones (upload_attempt, folder_id). It adds value by specifying the file_hash format and size limits, which are not in the schema. Slight deduction for not explaining content_type or folder_id semantics.

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: to prepare or reconcile a tenant-owned creative upload using a credential-free contract. It distinguishes itself from siblings like creatives_request_upload by version suffix and by specifying the unique behavior (returns upload_endpoint or dedup_success). The verb 'request_upload' plus the explicit conditions make it 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 states when to use this tool: when needing to request or reconcile an upload, with a stable idempotency_key. It also provides clear exclusions: it never returns upload_url, r2_key, or credentials, and it specifies the exact follow-up action (send bytes to the returned endpoint with Authorization header). This is more than most descriptions, making alternatives obvious.

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