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

The description goes beyond annotations by specifying upsert semantics and that the full updated policy set is returned. It also discloses the Lane 2 exception behavior with BROWSER_CONFIRMATION_REQUIRED. Annotations already indicate readOnlyHint=false, idempotentHint=true, and destructiveHint=false, and the description aligns with them, adding valuable context without contradiction.

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 dense but appropriately structured: it opens with the purpose, then details the policies format, then behavior, and ends with the exception. Every sentence carries information, though the typo ('follow-up, --') slightly mars otherwise clean presentation. It is not overly long for the complexity it manages.

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's complexity—multiple policy types, upsert semantics, and conditional exceptions—the description covers everything an agent needs to call it correctly. It explains the policy types, the behavior, the return value, and the alternate tool for loosening. The existence of an output schema means return-value details are unnecessary, and the description is complete for this level of complexity.

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?

With 0% schema description coverage, the description compensates by thoroughly explaining the policies parameter: the structure of objects, the enum of policy_type with its accepted value keys, and the optional enabled field. wallet_address is self-explanatory, and caller_id, though not described, is optional with a default and its purpose is inferable. The main parameter is well covered, though the others rely on name intuition.

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 configures trading limits and rules on an agent wallet, specifying a precise verb and resource. It distinguishes itself from the sibling tool request_wallet_policy_loosening by explicitly naming the alternative condition, and it narrows the scope to the caller's own wallet, eliminating ambiguity.

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?

Explicit guidance is given: on a Lane 2 wallet, if a change would loosen a server-enforced default, the agent should call request_wallet_policy_loosening instead. The description also notes that perp leverage cap is not a policy_type here, preventing misuse. This directly addresses when to use this tool versus alternatives and when not to use it.

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