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

Beyond readOnlyHint/openWorldHint the description adds real behaviour: nothing is sent, a breach returns mandate_violation plus the failing rule, a pass still requires human approval, and a router key is required for auth. That is meaningful context an agent could not derive from the annotations. The final sentence about the verification being recorded when the payment is prepared inside a payment run is vague about whether this call alone persists anything.

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?

Five short sentences, front-loaded with purpose and outcome before the auth note, with no filler or repetition of the schema. Every clause carries distinct information except the slightly muddy closing sentence about recording.

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 nine-parameter read-only check with no output schema and minimal annotations, the description covers the essentials: no side effects, the failure signal name, and the approval follow-up. What a pass actually returns, and whether the call persists the verification itself, remain unclear.

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 100%, so all nine parameters are already documented, and the description only adds that a router key is required (mapping to access_key). It says nothing about required vs optional semantics, the corridor pairing of from/to, or how cost_above_official_pct affects a verdict. Baseline 3 applies when the schema carries the parameter burden.

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 opens with a specific verb and resource plus scope: 'Verify one payment against a mandate before it is prepared.' That is clearly distinguishable from preparation/submission tools, and the 'one payment' scope rules out batch interpretation. It stops short of naming a near-neighbour such as check_constraints or payment_controls, so an agent must infer the boundary itself.

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?

'before it is prepared' gives a clear point in the workflow at which to call this, and the note that a pass still requires a named human approver tells the agent this is not a terminal gate. There is no explicit when-not guidance or named alternative for overlapping checks (e.g. check_constraints, payout_preflight).

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