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

With no annotations provided, the description carries the full burden, and it does add two real behavioral facts: the tool is stateless (caller must supply history) and it costs nothing to call. It omits the decision thresholds, side effects, and whether it consumes budget counters, so for a budget/fallback-routing gate the disclosure is only partial.

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 short sentences with no padding, but the ordering is poor: it front-loads the enum of verdicts rather than the tool's purpose, so the most orienting information arrives last. It is compact without being well-structured.

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 11-parameter, budget-aware gate with zero schema coverage and no annotations, the description is far too thin — it does not explain the cost/budget inputs, the stage distinction, or how defect inputs drive the verdict. The presence of an output schema excuses it from documenting return values, so the verdict list is arguably redundant, but the input-side gaps remain.

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% across 11 parameters, so the description must compensate. It explains only shot_history and its nested 'record_this_attempt' shape; model, render_cost_usd, stage, semantic_defects, technical_issues, project_spent_usd, project_budget_usd, visually_reviewed, fallback_model, and notes are all left undocumented anywhere.

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 never states a verb+resource; it opens with the verdict vocabulary (PASS / NEEDS_VISUAL_REVIEW / RETRY_SAME_MODEL / ...) so an agent must infer that this is a QA gate that evaluates a render and returns one of those decisions. The name plus the verdict list make the purpose guessable, but it is never explicitly articulated and there is no differentiation from siblings (which are unrelated utility tools anyway).

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 gives one concrete usage rule — 'Stateless: pass earlier attempts for this shot in shot_history' — which tells the caller how to get correct behavior across retries. It does not say when each verdict is emitted, what conditions trigger HALT vs HALT_BUDGET, or when to prefer this tool over alternatives, so the 'when to use' story is implied at best.

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