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

Annotations already mark readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the bar is lower. The description adds genuinely fresh context: the call itself is free (FREE approval checkpoint) while resuming starts the paid dependent animation, and the server rechecks the live credit balance only at resumption time. This cost-shaped timing detail is not expressible in 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?

Five sentences, each earning its place: FREE label, exact calling condition, user-facing workflow, no-op consequence of declining, and credit-order detail. The gate condition is front-loaded so an agent can reject invocation in one step, and there is no filler or restating of schema content.

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?

The full human-in-the-loop workflow, the exact gating values, the no-op semantics, and the credit-timing behavior are all present, which is significant completeness for a tool with a nested 8-direction schema and no output schema. Slight gap: post-submission behavior on a failed live credit check or the return value of the approval identifier is unnamed, but nothing an agent needs to decide whether and how to call 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 coverage is 100 percent, so the schema already documents every parameter, including the required 8-direction keys, ranges, and the primitive omit-to-keep semantics for poseScales. The description only restates the submission workflow (adjust the proposed frameIndices and poseScales, submit all eight) rather than adding new meaning, so the schema carries an appropriate baseline 3.

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?

Specific verb plus resource: the tool approves directional poses by presenting the eight previewUrls and submitting all eight adjusted indices and scales. It is sharply distinguishable from the many downstream job tools, because the precondition trio (status, wizardPhase, directionalPoseReview) defines exactly what this checkpoint is.

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?

Use-only-when condition is explicit, referencing the exact get_job fields that must hold. The when-not is equally explicit: closing or declining means do not call this tool, and the description states the consequence, the job stays paused and no dependent credits are spent. Together this fully routes an agent on when invocation is permitted.

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