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

Annotations already declare destructiveHint=true and openWorldHint=false, and the description adds strong behavior: idempotency, fixed bounded concurrency, input-order preservation, and a data-disclosure guarantee (no storage keys, hashes, provider bodies, tenant IDs). It does not disclose the destructive side effects implied by destructiveHint=true (e.g., what storage state is altered or removed), which is the one behavioral gap.

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?

Front-loaded with the core action and batch scope, then reason_code semantics, concurrency/security constraints, then the REQUIRED/EXAMPLE block. Dense but every sentence carries operational information; slightly packed given the single-paragraph run-on of constraints.

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?

No output schema exists, and the description compensates by describing the return shape (order preserved, redacted fields) and pointing at readiness.retryable/reason_code/next_action as the decision surface. Complete enough for invocation, with the only omission being the destructive side effect and connection_context.

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 must carry semantics; it constrains creative_ids to 1..20 unique IDs sourced from creatives_list and supplies a call example. The second parameter (connection_context) is never mentioned, though it appears to be a platform-wide context field.

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?

States a specific verb+resource ('reconcile ... creative IDs') plus scope (1..20 tenant-owned IDs, single server-side batch). It explicitly distinguishes itself from the sibling it could be confused with ('do not fan out creatives_confirm_upload calls').

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?

Gives explicit when-to-use (use readiness.reason_code to distinguish pending bytes, verification, terminal failure, create eligibility) and when-not-to-use ('do not fan out creatives_confirm_upload'), plus a retry condition ('Retry only when readiness.retryable=true and follow readiness.next_action').

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