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

Annotations only give the generic safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds genuinely non-obvious behavior: the call is a staged preparation rather than a persistence, it returns a pending_write_id, and committing requires an explicit user confirmation through a sibling tool. That is the kind of operational context annotations cannot express.

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 operationally critical facts (no immediate save, pending_write_id, explicit confirmation) are correctly front-loaded, but roughly half the text is a generic data-accuracy/attribution policy block that is not specific to this tool and would read identically on many other definitions. That boilerplate dilutes an otherwise tight, well-ordered description.

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?

Although there is no output schema, the description covers the return value (pending_write_id) and the full lifecycle needed to call the tool correctly, including the follow-up commit step and its confirmation requirement. Nothing an agent needs to avoid a mistaken silent write is missing.

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 description coverage is 100% and both parameters ('text', 'context') are already documented in the schema, so the baseline is 3. The description adds no format, length, or content guidance for the decision text or context beyond what the schema states.

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 ('Prepare a write to the canonical decisions log') and immediately qualifies the scope with 'this tool does not save immediately', which distinguishes it from canonical_decisions_list and canonical_pending_commit. An agent can identify its role in the two-phase write flow without opening any 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?

Explicitly names the trigger conditions ('when the user wants to log a decision or when you ask Log to canonical decisions?') and the exclusion ('Never silently log decisions'). It also names the alternative and the condition for invoking it ('Commit only after the user explicitly says yes by calling canonical_pending_commit'), which is exactly the when/when-not/alternative guidance the rubric rewards.

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