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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the hard gate that a pending write must be user-confirmed before committing, plus where the pending_write_id comes from. It stops short of stating what the commit does to the pending record or whether it is reversible/repeatable.

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, precondition, and ID provenance are front-loaded and earn their place, but the trailing attribution-footer and data-accuracy-contract paragraphs are generic boilerplate that applies to any tool in this family rather than this one. They pad the definition and dilute the key gating instruction.

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?

For a 2-param, non-idempotent, destructive commit with no output schema, the definition covers purpose, precondition, and parameter sourcing. It does not describe the post-commit effect (e.g., whether the pending entry is consumed or what the tool returns on success), which is the main remaining 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 coverage is 50% (only user_confirmation is documented in-schema), so the description has to compensate. It does so usefully: it says pending_write_id must come from canonical_facts_set or canonical_decisions_add, and that confirmation must follow an explicit yes, which matches the accepted values described for user_confirmation.

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?

States a specific verb and resource ('Commit a pending canonical fact or decision write') and clearly distinguishes itself from siblings by naming the tools that produce the pending_write_id (canonical_facts_set, canonical_decisions_add) and implicitly excluding the cancel path. An agent can tell exactly what this does without opening the schema.

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 when/when-not: only call after the user explicitly confirmed yes, and 'Do not call unless the user has just confirmed the exact pending write.' It also points to where the required ID originates. Routing and preconditions are fully covered.

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