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

With no annotations, the description carries full burden. It transparently discloses that it's a write operation, requires auth, yields a new immutable version, applies platform defaults to omitted fields, and includes defaulted fields in the response. This goes beyond minimal and addresses potential side effects.

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 reasonably concise for the amount of information, though the long sentence about defaults could be broken down. It front-loads purpose and key constraints (immutability, auth, schema), with no redundant words.

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 tool complexity (nested object policy, mutation, no annotations, no output schema), the description covers the essential operational details: auth, schema reference, required fields, default application, and response's `defaulted` list. It does not describe the full response shape, but the schema reference and sibling context help fill the gap.

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 the schema even gives a concrete example. The description adds extra semantic value by referencing the external schema, naming required fields, and explaining default behavior, which is not in the schema itself.

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 identifies the verb ('Create or update') and resource ('the wallet's treasury policy'), and distinguishes from siblings by noting immutable versioning (PUT creates the next version), which differentiates it from tools like get_policy that only read.

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 says when auth is required and what body must match, providing useful constraints, but it does not explicitly state when to use this tool vs alternatives (e.g., when to read with get_policy vs create/update here) or when not to use it. Some guidance is implied but not fully explicit.

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