stg_qa_gate

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

With no annotations, the description carries the full burden, and it does disclose two meaningful traits: it records the attempt and its cost in a local project ledger (a side effect), and it is 'Free (needs a license, uses no checks)' (cost/auth profile). It stops short of describing what each disposition triggers downstream or whether the ledger write is idempotent, so the behavioral picture is 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?

The disposition set and the required inputs are front-loaded, and the remaining sentences each carry distinct information (fix suggestions, param sourcing, ledger side effect, cost). It is dense but not padded, though the mid-paragraph param notes make it slightly run-on.

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?

An output schema exists, so return values need not be explained. But for a no-annotation, 11-parameter, mutation-and-ledger tool, the description leaves most parameter meanings and the consequences of each decision branch unstated, so it is only adequately complete.

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 two of them (technical_issues and semantic_defects, including the 'other' + notes convention), leaving project, shot_id, model, render_cost_usd, stage, fallback_model, visually_reviewed, notes, and project_budget_usd undocumented 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 and resource ('Decide what to do with a render') and enumerates the exact disposition set (PASS / NEEDS_VISUAL_REVIEW / RETRY_SAME_MODEL / SWITCH_TO_FALLBACK / HALT / HALT_BUDGET), which an agent can act on. It also ties itself to a sibling by naming stg_inspect_render as the source of `technical_issues`. Sibling differentiation against the other tools (stg_account, stg_pricing, stg_spend_report) is only implicit.

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?

Usage is implied through the data-flow references ('the issues array from stg_inspect_render', 'what you saw in the review frames'), which suggests this runs after inspection and review. However, it never states explicitly when to invoke this gate versus the siblings, nor when not to use it, leaving the sequencing to inference.

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