propose

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

Annotations already indicate idempotentHint=true and destructiveHint=false. The description adds that the operation is a proposal and does not mutate the live graph, which is more specific than the non-destructive hint. It also implies a write operation (readOnlyHint=false) by saying 'records,' which is consistent. No contradiction found.

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 two concise sentences. The purpose is front-loaded in the first sentence, and the key behavioral note (no live graph change) is in the second. No redundant information, every word earns its place.

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?

Given the tool's complexity (8 params, 4 required, nested ops objects), the description leaves significant gaps: it fails to explain parameter semantics, the relationship to commit, or the meaning of the output (though output schema exists). An agent would struggle to correctly invoke this tool without additional context on required fields like read_set and ops.

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 0%, so the description must compensate for explaining parameters. It only vaguely mentions 'non-empty read_set' and 'idempotency key' but does not explain what they mean, how they relate to the schema's fields, or what ops expects. With 8 parameters and 4 required, this is insufficient guidance.

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 states the tool records operations as a change proposal and explicitly notes it does not alter the live graph, distinguishing it from commit. The verb '기록합니다' (records) and resource 'change proposal' are specific and unambiguous.

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 implies usage by stating 'this call alone does not change the live graph,' suggesting that actual changes require another step (likely commit). However, it does not explicitly name alternatives or specify when to use this tool versus siblings like commit. The guidance is implicit rather than explicit.

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