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

Despite the annotations (readOnly=false, destructive=false, idempotent=true), the description adds rich behavioral detail: explains what each mode does to mutating tools (deny, propose, execute), mentions the audit row logging, and notes that auto_within_policy is capped by WalletPolicy. This goes beyond the annotations and provides critical context for the agent.

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 efficient, covering the action, the ladder, the mode semantics, the alternative, and the audit log in a compact paragraph. Every sentence adds value with no 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?

The tool is complex (three modes with different execution paths), and the description covers all of them with precise semantics, including the proposal flow and the policy cap. It also connects to sibling tools (set_wallet_policy, approve_proposal) and to the audit log. The only missing context is caller_id, but the overall completeness is high.

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?

The input schema has no descriptions (0% coverage), so the description carries the burden. It thoroughly explains the 'mode' parameter with its three values and their effects. 'wallet_address' is self-explanatory. However, 'caller_id' is never mentioned, which is a minor gap for an optional parameter.

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 immediately states the core function: 'Change an agent wallet's session permission mode'. It specifies the resource (wallet session permission mode) and the verb (change). It also distinguishes itself from sibling set_wallet_policy by noting the permission_mode can be set inline there, and references approve_proposal for the propose mode.

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?

It mentions an explicit alternative: 'Also settable inline via set_wallet_policy's permission_mode param.' However, it doesn't explicitly state when to prefer this tool over that alternative, nor give exclusions. Still, it implies use for directly changing the session permission mode ladder.

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