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

Annotations already flag destructive/open-world/non-idempotent, and the description adds real context beyond them: freeze requires freeze access, a two-person shut-off causes a freeze to wait for a second person, limits are set at the platform level, and the agent should confirm with the user before mutating. That is concrete operational behavior an agent needs before calling.

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?

Almost every clause carries information, but it is delivered as one unbroken run-on with nested parentheses and no front-loaded summary sentence. The reader must parse rather than scan, which costs comprehension on a six-action tool.

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 six-parameter, six-action mutation tool, the description covers each action's inputs, the access prerequisite, the two-person approval flow, and the list return fields. An output schema exists so return values need no explanation, leaving only minor gaps around failure modes.

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 carries the full burden, and it does map meaning onto every parameter: agent (including the opaque '-' for a person's card and '' to read from the card), card_id, freeze_id for confirm, limit_usd as a monthly platform limit, and incident_id as a recording target. The cryptic sentinel values are exactly the kind of semantics a bare pattern string cannot convey.

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 enumerates the six actions (list, assign, freeze/unfreeze, confirm, limit) against the resource implied by the title, so an agent can infer this manages per-agent payment cards. But there is no lead sentence stating what the tool is for, and nothing distinguishes it from close siblings such as limit_request, limits, waiting_shut_offs or confirm_shut_off.

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?

Usage is only implied by the action list; there is no explicit when-to-use or when-not-to-use guidance and no routing to alternatives. The one explicit directive, 'Confirm with the user before changing a card,' is a useful guardrail but not selection guidance.

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