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

Annotations already declare readOnlyHint=false, destructiveHint=true and openWorldHint=true, so the safety profile is known; the description goes further by explaining the billing model: charges accrue per delivered result at the quoted rate plus listed checks, capped by the user-approved ceiling. That ceiling-enforcement guarantee is real information an agent cannot get from annotations or schema. It stops short of saying whether charges are immediate or async, or what recourse exists after over-spend risk.

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?

Three tight sentences: the action and its prerequisite come first, the parameter semantics second, the billing guarantee last. No filler, no restatement of the title, and every clause carries new information for the caller.

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 a destructive, money-spending tool with five parameters, zero schema description coverage and no output schema, the definition covers the essentials of how to call it but not what comes back. It never says what identifier or result an agent should expect on success, nor how a replayed idempotency_key behaves, and authority_id is undocumented. Adequate to invoke, thin for handling the response.

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%, so the description must carry the meaning, and it does for four of five parameters: quote_id/quote_hash identify the approved quote, confirm_max_cents is the ceiling the user approved in cents, and idempotency_key is described as stable (signaling safe retry). The optional authority_id is never mentioned, and quote_hash's role as an integrity binding for the approved terms is only implied.

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 states a specific action on a specific resource: it starts paid work against an approved quote and incurs charges at the quoted rate. An agent can tell this is the spend/execute step rather than a read. However, it never names the sibling it pairs with (quote_capacity_work, which presumably produces the quote_id/quote_hash), so differentiation from the quoting step is left 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?

"Starts the work on an approved quote" implies the prerequisite that a quote must already exist and be approved, which is useful context. But there is no explicit when-not guidance, no statement of what to do first (call quote_capacity_work), and no mention of alternatives such as claim_free_capacity or create_capacity_refund_claim. Usage is inferable rather than stated.

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