propose_mutation

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

With no annotations provided, the description carries the full behavioral burden. It discloses the critical safety property that the tool does not execute the mutation, and it also describes what the tool generates: a proposal token and a dry-run query plan. It does not cover the downstream review/approval workflow, but the most important behavior is transparent.

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?

Three short declarative sentences deliver the purpose, the key negative behavior, and the generated outputs without filler. The HITL context is front-loaded, and every sentence 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?

For a one-parameter tool with an output schema, the description covers the essential behavior and output artifacts well. It is slightly thin on how the returned proposal token is meant to be used downstream and on SQL parameter constraints, but nothing critical is missing for an agent to decide to use this tool over apply_mutation.

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?

The schema only declares a string parameter named sql with no description, so the description's mention of 'INSERT, UPDATE, DELETE' and 'dry-run query plan' adds meaning about the expected SQL content. However, it does not elaborate on syntax, limits, or which SQL forms are rejected, and with 0% schema description coverage the parameter semantics are only partially compensated.

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 opening line names the tool as a 'Human-in-the-Loop (HITL) Proposal Tool' and states it 'submits a proposed data mutation' for review, listing INSERT, UPDATE, and DELETE. The explicit 'Does NOT execute the mutation' distinguishes it from sibling apply_mutation and makes its role unmistakable.

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 clearly establishes the intended context: use this tool to propose a mutation for review, not to execute one. The negative clause 'Does NOT execute' implies the alternative, but it does not explicitly name apply_mutation or state a firm when-not condition, so it stops short of full guidance.

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