validate_draft_result

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

With no annotations provided, the description carries the full burden of behavioral transparency. It explicitly states that the original file is not modified, that a temporary copy is used, and that the temp file is always deleted. This gives an agent a clear sense of side effects and safety. It does not cover error behavior or failure modes, but the main behavioral guarantees are disclosed.

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 generally clear but contains some redundancy: the first sentence and the second sentence both describe the same core purpose, repeating 'without modifying the original file' and 'status/summary.' The Args and Returns sections are helpful, but tightening the introductory sentences would improve conciseness without losing information.

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?

The description covers the main contextual points: what the tool does, when to use it, side effects, inputs, and the shape of the return value. It includes enough information about the output (status, summary, executed_at, next_actions, optional results) for an agent to understand the result. It could include details on error raising or the exact structure of the results, but that is not essential for initial selection and invocation.

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 description adds meaningful detail beyond the bare schema, explaining that structured_update_json is a 'Draft in UpdateRequest shape (instructions array)' and that actor_contact is optional with a system placeholder when omitted. This helps an agent understand the nature of the parameters. The excel_path parameter is simple, but the description still clarifies its role as the path to the COBie Excel file.

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 that the tool validates a draft update without modifying the original file, using a temporary copy. It specifies the resource (workbook state after applying a draft) and the action (validate), and it distinguishes itself by emphasizing the read-only nature and pre-commit usage. However, it does not explicitly name sibling tools like update_cobie or validate_cobie, so the differentiation is clear but not as explicit as it could be.

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 provides explicit usage guidance: 'Use before commit to block Apply when the result would be invalid.' This tells the agent when to use the tool and implies it should be used for validation prior to committing changes. It does not explicitly mention alternatives for applying changes, which slightly reduces clarity, but the primary usage context is well defined.

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