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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: the four gates (identity, mandate limit, behavior policy, risk) and the outcome states ('pending' settled via webhook, 'denied', 'escalated'). It stops short of spelling out irreversibility or the retry semantics the idempotency_key param implies.

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?

Two dense, front-loaded sentences; the core action leads and the gating/return-state detail follows. The telegraphic gate list ('identity · mandate limit · behavior policy · risk') is compact and earns its place.

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 appropriately names the three possible return states and the webhook settlement path, and all 7 params are documented. Complete enough for an agent to call and interpret results, with only minor gaps around retry/irreversibility.

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 the schema already documents all 7 parameters including currency/mandate matching and the idempotency_key resume handle. The description adds only the implicit 'spend mandate' requirement, not new syntax or format detail, so baseline 3 applies.

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+resource with scope ('Pay from THIS agent's Custodian custody wallet'), which is clear and disambiguates whose wallet is charged. It doesn't distinguish itself from payment-adjacent siblings like request_budget or card_link, but no sibling performs this exact action.

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?

Prerequisites are given (active wallet + spend mandate) and the gate conditions are listed, implying when the call can succeed. However there is no explicit guidance on when to choose pay versus alternatives such as request_budget or card_link, so usage is only implied.

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