excel_add_worksheet

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

Annotations already mark this as destructive/non-readonly, so the bar is lower, and the description does add useful context: the 'effect' parameter is a claimed read/write that Spring verifies, and approval_ref is used when resuming a write. This conveys the write-approval flow reasonably. However, it does not go deeper into what makes the operation destructive or what happens on the target workbook.

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 parameter list is compact and scannable, and the routing constraint is front-loaded. But the first line wastes space by restating the name, and the one-line parameter labels could have been tighter. It is adequately structured but not exemplary.

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?

Given the 0% schema coverage, a write operation that is marked destructive, and the fact that all Excel-specific behavior lives inside the opaque 'arguments' JSON, the description is not sufficient. The output schema covers return values, but an agent has no way to know what to put in 'arguments' to actually create a worksheet, whether a worksheet with the same name is replaced, or what preconditions apply.

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?

With 0% schema description coverage, the description must carry the burden, and it does add labels to each parameter: project_id is an authenticated UUID, connector_account_ref is a project-bound alias, idempotency_key is a stable business-action identity, and effect is a verified read/write claim. However, the most important parameter, 'arguments', is only described as 'JSON string of arguments for the connector operation' — an agent still cannot tell what fields are needed to add a worksheet (e.g., sheet name, position). So it partially compensates but leaves the key semantics unresolved.

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's first sentence merely restates the tool name: 'Excel connector operation add_worksheet (platform tool excel.add_worksheet).' It never states the actual behavior in domain terms, such as 'adds a new worksheet to an Excel workbook.' A reader must infer the action entirely from the name rather than from the description.

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 routing constraints ('Routes only through the exact project/account governed connector authority') but no guidance on when to use this tool versus alternatives like excel_update_range or excel_list_worksheets. There is no when-to-use rationale, no exclusions, and no mention of sibling tools.

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