batch_resume

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

Goes well beyond the annotations: billing semantics ('billed as they finish'), concrete return behavior on an ended run ('final status and already_ended:true'), and the exact credit failure codes (BATCH_INSUFFICIENT_CREDITS, BATCH_KEY_CAP_REACHED). This is the kind of operational detail the idempotentHint/destructiveHint flags cannot convey.

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?

Two tight sentences plus a short credit footnote; every clause carries distinct information (action, billing, idempotency, ended-run return, error codes) and the primary purpose is front-loaded.

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?

With no output schema, the description compensates by describing the important return signal (already_ended:true) and the failure modes, plus cost behavior. Nothing an agent needs to invoke this correctly against its siblings is missing.

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 100% and the single job_id is fully documented as 'Batch job id returned by batch_create or batch_list'. The description adds no further parameter meaning, so the baseline 3 applies.

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 (Resume) and a precisely scoped resource (a paused Batch run), which an agent can distinguish from the counterpart sibling batch_pause. It does not explicitly differentiate from batch_rerun or batch_cancel, so sibling separation relies on inference rather than the text.

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?

It establishes the precondition (only meaningful on a paused run) and describes behavior for the not-paused and already-ended cases, which functionally covers when the call is a no-op. It never names an alternative tool for those cases, so the routing guidance is implicit rather than explicit.

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