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

Goes well beyond the annotations: parallel execution, hard max_usd refusal semantics ('nothing runs'), per-key billing identical to a direct call, failed steps being free, and the shape of the returned sections/receipt/citations. This is exactly the pricing and failure behavior an agent needs before committing.

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 dense sentences that are front-loaded with the core action and pack the billing, cap, and return details without filler. The clause stacking in the first sentence makes it slightly harder to parse than it needs to be, but nothing is wasted.

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?

There is no output schema, and the description compensates by naming what comes back (per-step sections with via_tool, via_input, rows with source_url, plus a receipt and citations). For a paid multi-step executor, the cost, failure, and output picture is 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: plan_id's origin in plan_official_records_query, the all-or-nothing nature of max_usd, and the fact that each step is billed like a direct call. It adds value over the schema's own field descriptions rather than restating them.

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?

Names a specific verb+resource ('Runs a plan') and explicitly ties the input to the sibling planner ('a plan from plan_official_records_query (its plan_id) or explicit steps'), so the agent can distinguish this executor from the planning tool without opening either schema.

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 two clear entry paths (plan_id from the planner, or explicit steps) and an operating constraint (all steps in parallel under a hard cap), which tells the agent when this tool is the right call. It stops short of saying when to prefer one path over the other or what to do when the cap refuses.

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