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

The description discloses key behavioral traits beyond annotations: it is free, calling it resumes paid dependent animations, and the server rechecks the live credit balance immediately before resuming. It also explains that declining leaves the job paused and no dependent animation credits are spent. This adds substantial context about side effects and safety, complementing the annotations (readOnlyHint=false, openWorldHint=true).

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 dense and long, but every sentence carries a specific, actionable rule. It is front-loaded with the usage condition, followed by process, conditional rules, and negative consequences. Some sentences could be tightened or structured into bullet points, but there is no fluff; the length is justified by the complexity of the tool.

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 tool with no output schema and complex conditional behavior, the description covers all essential aspects: when to use, how to present previews, how to handle unreviewed candidates, special handling for directions present/absent, and consequences of not calling the tool. The server-side credit recheck is also disclosed, making the agent fully informed to call it 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?

Although the schema has 100% coverage with descriptions for all parameters and nested object properties, the description enriches semantics with critical operational instructions: use unique indices 0–3, keep scale 100, preserve unused map entries, and let the user adjust or review the proposed frameIndices and poseScales. These are not apparent from the schema alone and are essential for correct parameter values.

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 identifies the tool as a 'FREE approval checkpoint' for directional poses in a job workflow, with the explicit purpose of submitting approved frameIndices and poseScales. It distinguishes itself from siblings by stating precise conditions under which it applies (status 'waiting_approval', wizardPhase 'waiting-directional-pose-approval', directionalPoseReview). The action is specific: present previewUrls, let the user adjust/review, and submit the maps.

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 explicit usage conditions: 'Use only when get_job returns status...' and states the negative case: 'Closing or declining means do not call this tool'. It also distinguishes between when directions is present (four poses) versus absent (eight poses), giving clear routing guidance. This leaves no ambiguity about when to invoke the tool versus alternatives.

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