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

Annotations indicate readOnlyHint=false and destructiveHint=false, and the description aligns with these. It goes beyond annotations by revealing tier-dependent cap enforcement (REGISTERED agents clamped to $25K, VERIFIED agents no ceiling), the AP2 compatibility requirement, and the fact that it can create or update. This adds meaningful behavioral detail about how the mandate will be handled.

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 sentences: the first states the core action, the second lists the constraint fields, and the third covers agent-tier rules. Each sentence is dense with essential information and no redundancy, with the purpose front-loaded.

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 8 parameters and an output schema present, the description covers the non-obvious business rules (agent tiers, cap clamping, AP2 formatting) and the prerequisite that anonymous agents must register first. The output schema handles return values, so the description is complete for guiding invocation and expectation-setting.

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 100%, so the baseline is 3. The description adds value by explaining that REGISTERED agents' caps are clamped to their tier limit, which directly affects the effective semantics of maxNotionalUsd and dailyCapUsd. It also maps the prose fields (counterparty whitelist, currency pairs, ESG floor, expiry) to schema properties, reinforcing their purpose.

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 'Create or update an AP2-compatible spend mandate for a REGISTERED or VERIFIED DPX agent' — a specific verb, object, and target. It enumerates the mandate fields and clearly distinguishes this from sibling tools like agent.kya_register and agent.kya_verify by focusing on settlement constraints rather than identity management.

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?

The description provides clear eligibility context: mandates are for REGISTERED or VERIFIED agents, and ANONYMOUS agents are explicitly excluded with the directive to 'register with ownerEntity + ownerEmail first.' This is helpful but doesn't explicitly name the alternative tools (e.g., agent.kya_register) or state when not to use this tool beyond the anonymous case.

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