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

Annotations already convey mutating/destructive intent. The description adds that this is the only recording path in the MCP context (no UI button) and that the proposal must be approved first. It could state whether the action is reversible or what happens to the pending proposal, but the destructiveHint reduces that burden.

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?

Front-loaded with a specific verb and object, then operational details. The 'only after explicit approval' warning is included in the correct final position without padding.

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 description covers the effect, the input source, the sole-path context, and the approval precondition. It does not describe what happens after commit or whether it is reversible, but the destructiveHint annotation and minimal parameter surface make this adequate.

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% with a brief description of 'proposal id'. The description adds meaningful provenance — the id must come from a propose_* tool or list_pending_proposals and must have been explicitly user-approved — which goes beyond the schema.

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 action ('commit a pending proposal to the user's finances') and distinguishes it from the propose_* tools that create pending proposals. It is explicit that this is the only way a proposal gets recorded, with no UI alternative.

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?

Provides explicit invocation conditions: use the proposalId returned by a propose_* tool or list_pending_proposals, and only call after the user has explicitly approved that exact proposal. This is strong when-to-use guidance with a clear prohibition.

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