review_generation_plan

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

Annotations only cover the safety profile (readOnlyHint false, destructiveHint false, openWorldHint false); the description adds substantive behavior beyond that: it deduplicates retries, shows universal credits only, flags high-price models and totals over 1000, keeps specialized entitlement costs internal, and explicitly states queries do not authorize generation or record consent. That is meaningful disclosure of output behavior and non-authorization, though the actual side effects of persisting a plan are not spelled out.

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?

Purpose is front-loaded and most sentences carry operational weight, but the single dense paragraph is jargon-heavy and overlaps with the schema descriptions of confirmation_mode and confirmed_plan_id. Some clauses (specialized entitlement costs remain internal) could be trimmed without loss.

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?

With no output schema, the description carries the burden of return-value explanation, and it only partially discharges this by implying what it displays (universal credits, high-price models, totals >1000). For a complex planning tool consuming flow_id, steps, submitted_steps and confirmation state, the description is adequate but leaves the returned plan structure and confirmed_plan_id lifecycle somewhat implicit.

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 100%, so the baseline is 3. The description reinforces semantics for confirmation_mode (latest explicit preference in this conversation, conditional default) and confirmed_plan_id (only after human approval of that exact plan), but largely restates what the schema descriptions already state. It adds little beyond the structured fields.

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?

States a specific verb and resource: it reviews the complete current creative flow before a paid submission, using saved quotes and submitted request IDs. That distinguishes it from siblings like estimate_image_cost (pure cost lookup) and generate_image (actual execution). It lacks an explicit mention of sibling alternatives, but the scope is clear.

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?

Gives real timing guidance ('before a new paid submission') and conditions for confirmed_plan_id ('only after human approval here'), plus the confirmation-mode default rule. However, it never names which alternative tools to use instead (e.g., estimate_* vs. generate_* vs. this review step), leaving the agent to infer the position in the flow.

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