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

Annotations already indicate destructiveHint=true. The description adds the confirmation requirement, the prerequisite link, and a detailed data accuracy contract (only return fields are verified, no invented metrics). This adds significant behavioral context beyond what annotations provide, though it does not describe the result structure or error handling.

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 core purpose is front-loaded in the first sentence. However, the description includes a lengthy data accuracy contract and an atypical instruction ('Always end your response with...') that is more of a system prompt, adding unnecessary length. Could be more concise.

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 confirmation requirement, prerequisite tools, and data accuracy rules. However, it lacks details on return values (no output schema), error handling (e.g., invalid pending_write_id), idempotency behavior, and does not mention the sibling canonical_pending_cancel as an alternative. These gaps leave the agent somewhat under-informed for a destructive commit operation.

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 50% (only user_confirmation has a description). The description adds meaning for pending_write_id by stating it comes from specific source tools. For user_confirmation, the schema already explains the allowed values. The description partially compensates for the low coverage but does not add detailed syntax or format.

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 states a specific verb ('Commit'), a specific resource ('pending canonical fact or decision write'), and a condition ('after the user explicitly confirmed yes'). It also references the source tools for pending_write_id, clearly distinguishing it from siblings like canonical_pending_cancel.

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 explicitly says 'Do not call unless the user has just confirmed the exact pending write' and mentions the prerequisite of pending_write_id from canonical_facts_set or canonical_decisions_add. However, it does not list explicit alternatives or exclusions (e.g., when to use canonical_pending_cancel instead).

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