csv_to_bundle

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

With no annotations provided, the description carries the full burden and does so: it discloses the underlying endpoint, that mapping is header-to-field with no model involved, that nothing is retained and no quota is consumed, and a ~1 MB input cap. It also warns that unmapped columns can silently produce a report that looks complete but is not, which is exactly the kind of non-obvious failure mode an agent needs.

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 front-loaded with the core action, then the parameter constraints, then the return values, then explicit WHEN TO CALL / WHEN NOT TO CALL headers. Slightly long, but every clause (size limit, no quota, unmapped-column warning) carries information an agent would otherwise lack.

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?

With no output schema and no annotations, the description steps in to describe the return payload (bundle plus mapped_columns, unmapped_columns, warnings) and instructs the agent to read those before running an agent. The only gap is the undocumented nested site_profile parameter, which is the one thing an agent could still get wrong.

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. It does well for two of three parameters: csv_text is clarified as inline file contents rather than a path with a size limit, and kind's enum values are spelled out. However, site_profile — a nested object — is never mentioned, leaving one parameter completely undocumented in both schema and description.

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?

Names a specific verb and resource (turn a raw CSV export into the bundle shape run_agent expects) and characterizes the inputs concretely (shift log, production/downtime spreadsheet). It also positions itself relative to the run_agent sibling, so an agent can distinguish the two without opening either schema.

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?

Explicit WHEN TO CALL (user has a spreadsheet and no namespace yet) and WHEN NOT TO CALL (data already arrives as structured UNS events, or the bundle can be assembled directly). Both the positive and negative conditions are stated, leaving nothing to inference.

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