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

Annotations only note readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the description carries the burden of explaining behavior. It adds meaningful context: the policy defines rules and once set, every payment is automatically checked via policy.check. This goes beyond the structured annotations, though it does not mention authorization, overwrite semantics, or return behavior.

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?

The description is three sentences: first states the action, second lists the key policy rules, and third explains the automatic enforcement via policy.check. It is front-loaded with the main purpose and every sentence contributes value with no repetition or filler.

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 create operation with 9 parameters and no output schema, the description covers the main purpose, key configurable rules, and the automatic enforcement consequence. It does not specify the return value/created policy identifier or whether creating a policy replaces an existing one, but the rich parameter schema and stated behavior make the tool sufficiently functional for invocation.

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% and each parameter has a detailed description. The description's enumeration of per-transaction ceiling, daily limit, hold threshold, blocked counterparties, allowed purposes, and oracle stability gate maps directly to schema fields, but it adds no new semantic meaning beyond what the schema already provides.

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 uses the specific verb 'Create' with a clear resource ('spending policy') and scope ('for an AI agent'). It enumerates the policy rules and distinguishes itself from the sibling tool policy.check by stating that payments are automatically checked via policy.check after creation.

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 context: this tool is used to set spending rules before financial actions. It indicates that policy.check is the follow-up mechanism, but it does not explicitly discuss when not to use the tool or compare against policy.delegate, so no exclusion guidance is given.

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