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

Adds substantial behavior beyond the annotations: the credit debit, the guarantee that the first call NEVER debits, the single-use nature of confirm_token, and its 300-second validity window. Annotations only say readOnlyHint=false and destructiveHint=false, so this description is what actually tells the agent a financial mutation occurs and how to stage it safely.

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 dense sentences with zero filler, front-loading the state transition, then the no-debit guarantee, then the confirmation mechanics. The two-phase flow is presented in the order the agent will execute it.

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 helpfully discloses the first-call return shape (requires_confirmation + confirm_token), which is otherwise undiscoverable. It leaves open what happens on token expiry, whether the declared cost amount is returned, and what occurs if credits are insufficient — relevant gaps for a debiting 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?

Schema coverage is only 25% (just confirm_token), so the description must compensate, and it does for the most failure-prone point: the second call must repeat the same step/pace/approach or the confirmation will not match. It does not explain what step (1-40) or pace semantically control, but the enum values for pace and approach are largely self-describing.

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 with an explicit state transition ("Move a mission HUNT→CHASE"), which is far more precise than a generic "start" verb. This distinguishes it immediately from read siblings like get_mission and from submit_mission_result, which handles the opposite end of the mission lifecycle.

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 a clear operational sequence: first call declares cost and returns requires_confirmation plus a token, second call with the token executes. That is strong when/how guidance for the tool's own flow, but it never states when a caller should prefer an alternative (e.g. list_missions to find a mission worth starting) or any precondition such as eligibility or credit balance.

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