propose_cleansing_plan

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

With only readOnlyHint=true in annotations, the description adds substantial behavioral context: it does not call an LLM, does not propose a plan itself, returns aggregate-only profiling data, exposes sensitivity classifications, and defines the accepted operation vocabulary and parameter constraints. This is exactly the kind of contract-level detail an agent needs before invoking the tool.

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 structured and mostly front-loaded, with the key contract details in the first sentence and the critical 'does not propose itself' clarification immediately after. It is somewhat longer than necessary and the initial 'propose a data-cleansing plan' phrasing is slightly in tension with the later disclaimer, but no sentence is wasted.

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?

There is no output schema, so the description must carry the return-value burden, and it does so reasonably well by explaining the profile, sensitivity classifications, vocabulary, and plan object shape. It still leaves some detail about the exact response structure and model_name format implicit, but an agent has enough to call it correctly and use the result.

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 would ideally explain model_name. It says the data is 'for a model,' which implies the single required parameter identifies the model, but it provides no format or selection details. With only one self-descriptive required parameter, the gap is moderate rather than severe.

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 specifies the concrete resources returned: an aggregate-only profile, per-column sensitivity classification with match_rate, and a closed operation vocabulary. It also distinguishes this tool from apply_cleansing_plan by naming it as the consumer of the finished plan. The only ambiguity is that the tool name says 'propose' while the description explicitly says it does not propose a plan itself.

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?

It clearly tells the agent to use the returned contract to build a plan and then pass that plan to apply_cleansing_plan. This establishes the workflow and names the relevant alternative. It does not give explicit when-not-to-use guidance, but the intended usage context is clear.

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