Workbooks Send Workbook

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real value beyond them: it discloses the underlying API contract (Sigma POST /v2/workbooks/{workbookId}/send) and previews the body's constituent fields — target list, configV2 format/element/page selection, plus optional parameters, conditions, timeout and sendAsUser. It stops short of stating permission requirements or whether sends are retractable, which is why this is not a 5.

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?

Two sentences, front-loaded with what the tool does and the available targets before the schema-detail sentence. The second sentence is dense but each clause names a distinct body field, so little 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?

The output schema exists, so return values need no explanation, and the annotations cover the read/write profile. For a two-parameter tool whose second parameter is an opaque object, the description supplies enough body structure for an agent to attempt a correct call without opening external documentation.

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% and body is an untyped free-form object, so the description carries the full burden — and it does so by naming the body's substructure (target, configV2, parameters, conditions, timeout, sendAsUser). It does not describe the shape of individual targets or the allowed configV2 format values, and it defers detail to an external API doc the agent may not have access to.

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 gives a specific verb (export/send) and resource (a workbook) plus a key scope qualifier: 'once' to one or more targets, and it enumerates the target types (email, Slack, Google Sheets/Drive, webhook). It does not name the nearby siblings that could be confused with it — workbooks_export_workbook, workbooks_export_and_download, or workbooks_add_workbook_schedule — so the agent must infer that 'once' is what separates this from a recurring schedule.

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 word 'once' implies this is the one-shot delivery counterpart to scheduling, and the target list implies delivery rather than local download, which is implied usage guidance. However, no alternative tool is named and no when-not conditions or prerequisites (e.g. target authorization, permission to send externally) are stated.

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