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

Annotations are minimal (no readOnlyHint, idempotentHint, or destructiveHint), so the description carries the burden of behavioral disclosure. It discloses that delegation can be revoked at any time (a key behavioral trait) and that the sub-agent can only spend up to the delegated ceiling. It does not, however, describe any permission requirements, audit trails, or side effects (e.g., whether delegation affects existing policies). The description adds meaningful context beyond annotations.

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?

Four sentences, each front-loaded with value: purpose, constraints, revocability, and use case. Zero wasted words, logical flow from what to why.

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?

Given the moderate complexity (6 parameters, all described in schema), the description covers the delegation concept, constraints, and use case well. There is no output schema, but the description doesn't discuss return values. However, for a delegation tool, the description adequately sets expectations about the operation. It could mention default behavior when optional fields are omitted, but the schema already hints at that.

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 beyond the schema by explaining the overall delegation relationship and limits (e.g., 'The sub-agent can only spend up to the delegated ceiling'), which semantically enriches parameters like max_total and max_per_tx. It does not, however, detail parameter-specific constraints or validation (e.g., that max_total must be positive). The description enhances understanding but could be more precise.

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 clearly states the tool delegates payment authority from a parent agent to a sub-agent with explicit limits, using specific verbs ('Delegate', 'revoked') and the resource ('payment authority'). It distinguishes from sibling tools like policy.create (creates policies) or policy.check (checks policies), as this specifically covers authority delegation in multi-agent workflows.

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 explicitly specifies when to use the tool: 'in multi-agent workflows where an orchestrator authorises a worker agent to make payments on its behalf.' It does not, however, mention when not to use it or explicitly name alternatives among the sibling tools, such as using policy.create for broader policy management. The guidance is clear and actionable but lacks exclusions.

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