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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false), but the description adds meaningful behavioral context beyond them: the requirement for an explicit spending limit and the idempotency-key retry contract. The idempotentHint=false annotation is mildly in tension with the stated safe-retry guidance, though the key parameter plausibly explains the mechanism rather than contradicting it.

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 tight sentences with the core action front-loaded and no filler. The retry guidance is associated with the idempotency key in a natural reading order.

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 an 8-parameter mutation tool with nested objects, 0% schema coverage and no output schema, the description addresses the highest-risk concerns (spending cap, idempotent retry, where results/cancellation live) but leaves the batch-specific semantics like combination_mode and project/input scoping unexplained.

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 the burden for all 8 parameters. It only clarifies two of them (max_credits as 'spending limit' and idempotency_key as 'stable idempotency key'); tool, name, input, settings, project_id and the zip/cartesian combination_mode enum are entirely unexplained in both schema and description.

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 gives a specific verb+resource ('Submit a single-tool batch') and frames the engine it runs on, so the agent knows this dispatches a batch when a single tool runs. It does not, however, differentiate itself from the sibling submit_job, which is the most likely source of confusion.

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 provides real guidance on retry behavior ('Reuse the same key and exact request after an uncertain response') and routes result/cancel handling to 'workflow run actions'. However, it never states when to prefer this over submit_job or start_workflow, leaving alternative selection to inference.

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