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

Annotations already declare non-read-only, idempotent and non-destructive, and the description adds substantial extra behavior: it consumes one estimate from the user's balance, requires explicit credit confirmation, refunds the reservation on provider failure, and cannot overwrite existing review work. These are exactly the side effects an agent must know before calling a metered mutation.

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?

Four dense sentences, front-loaded with the action and its cost implication, then confirmation, retry, and failure semantics. No filler and nothing repeated from the annotations.

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 shape need not be spelled out, and the description still clarifies the output is extracted quantities for review rather than a bid-ready estimate. Billing, idempotency, refund, and overwrite behavior are all covered for a 3-param metered mutation.

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?

With 0% schema description coverage the description must carry parameter meaning, and it explains two of three: confirm_credit_use (must be true only after explicit user confirmation) and idempotency_key (reuse on retry to prevent duplicate charge). project_id is only implied by 'a new project', leaving a minor gap.

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 ('run the initial AI takeoff') and resource ('a new project with an attached plan PDF'), which cleanly separates it from get_takeoff (retrieve) and attach_plan_pdf (attach). An agent can identify this as the initiating extraction call without opening the 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 clear context for use (new project, plan already attached, initial run) and a concrete precondition for the confirm flag plus retry guidance for the idempotency key. It does not explicitly name sibling alternatives for the retrieve/re-export cases, but the scenario framing makes the routing inferable.

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