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

With no annotations provided, the description carries full burden and delivers: idempotency, bounded concurrency, input-order preservation, and non-exposure of sensitive data. It also explains retry behavior, covering operational nuances an agent needs to invoke 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?

The description is thorough yet efficient, front-loading the core purpose and systematically covering usage, constraints, and an example. Every sentence contributes value, with clear formatting (REQUIRED, EXAMPLE) that aids parsing.

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 single-parameter reconciliation tool with no output schema, the description is remarkably complete. It explains the readiness.reason_code semantics, retry rules, what results preserve, and what they never expose, giving an agent all necessary context 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 coverage is 0%, so the description fully compensates by specifying the parameter type (list[str]), constraints (1..20 unique IDs), and source ('from creatives_list'). This adds meaning beyond the bare schema and gives precise, actionable guidance.

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 action ('reconcile'), the resource ('creative IDs'), and its scope ('1..20 tenant-owned creative IDs in one server-side batch'). It explicitly distinguishes itself from a sibling by saying 'do not fan out creatives_confirm_upload calls', providing strong differentiation.

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 gives explicit when-to-use guidance via readiness.reason_code distinctions and retry conditions ('Retry only when readiness.retryable=true and follow readiness.next_action'). It also explicitly warns against using an alternative ('do not fan out creatives_confirm_upload calls'), making usage context unambiguous.

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