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

Annotations provide only readOnlyHint=false and destructiveHint=false, so the description carries the burden for behavioral context. It clearly conveys partial-update (PATCH-like) semantics, which is a meaningful behavioral trait beyond the annotations. It does not go into side effects like full replacement of rows, but that is documented in the schema for raw_data.

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 a single efficient sentence with no filler. The core action and the partial-update behavior are front-loaded, and the example payload is compact and useful without redundancy.

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 moderate-complexity update tool, the combination of the description, fully documented schema, and output schema covers the essentials: what the tool does, partial-update semantics, and parameter meaning. It could be more complete by naming when to use it versus creating or archiving a dataset, but nothing critical is missing for invoking it correctly.

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%, so the baseline is 3. The description's example list '{ raw_data, columns }' adds little beyond the schema's own field descriptions, since both parameters are already fully documented there.

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 states a clear verb and resource: 'Update a custom-data dataset'. It also communicates the key semantic distinction from creation tools by noting 'send only the fields you want to change'. However, it does not explicitly differentiate from sibling tools like create_custom_data or archive_custom_data beyond the verb 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?

The phrase 'send only the fields you want to change' implies the tool is for partial updates to an existing dataset, which is useful context. But there is no explicit guidance about when to choose this tool over alternatives such as create_custom_data, duplicate_custom_data, or archive_custom_data, nor any stated exclusions.

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