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

Annotations already indicate a write operation, and the description adds valuable specifics: upfront quota charge, no refunds for failed rows, and plan caps. This goes beyond the generic annotation flags and informs cost-sensitive decisions. No contradiction with annotations.

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 sentences with high information density. Front-loads the core action, then requirements, then consequences, then next step. No redundant phrasing.

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?

Covers the essential workflow: submit, get job id, check bulk_status. Warns about costs and caps. Since output schema is absent, the description compensates by stating the return value. Sufficient 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 covers all parameters with descriptions, so baseline is 3. Description adds meaning by explaining the template placeholder pattern and the one-object-per-label data structure, which clarifies the relationship between zpl and rows. Also notes the per-row quota impact.

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: submitting a bulk label production job with a ZPL template and data rows. Clearly distinguishes from siblings like zpl_preview by describing the batch nature and the one-object-per-label structure.

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?

Provides context for when to use: requires an API key with bulk jobs plan and points to bulk_status for follow-up. It doesn't explicitly name alternatives, but the bulk-specific semantics make the use case clear. Could be improved by stating not to use for single-label jobs.

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