microsoft_list_sharepoint_drives

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds the governed-routing constraint and confirms effect must be 'read', which aligns with readOnlyHint. However, it drags in inapplicable boilerplate — approval_ref is described as 'when resuming a write,' which is irrelevant to a read-only operation and could mislead; this is noise rather than a direct annotation contradiction.

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 compact and well-structured as an arg list, with each parameter getting a short line. Minor waste exists: the first line duplicates the tool name, and the approval_ref line is generic boilerplate, but overall the text is efficient and front-loaded with the operation identity and routing constraint.

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?

While the output schema covers return values and annotations cover the safety profile, the definition omits the operational core: what to put inside `arguments` for a list-drives call and how this tool relates to the sibling Microsoft list tools. For a wrapper with 0% schema coverage, the invocation payload is the most critical missing piece, so the description is incomplete for correct 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?

Schema description coverage is 0%, so the description must compensate, and it does provide one-line semantics for all 7 parameters (authenticated UUID, correlation reference, connector alias, etc.). The critical `arguments` parameter, however, is only described as 'JSON string of arguments for the connector operation' without stating which arguments are valid for listing drives (e.g., site scoping, pagination), leaving the agent to guess the payload.

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 opens by restating the operation name ('Microsoft connector operation list_sharepoint_drives') rather than explaining what the operation does; it never states the tool lists the drives available in the connected SharePoint environment. The verb+resource is inferable from the name, but the description does not differentiate it from siblings like microsoft_list_sharepoint_sites, microsoft_list_sharepoint_drive_items, or microsoft_list_drive_files.

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?

No guidance is given on when to use this tool versus the many connector siblings or the generic connector tools (list_connectors, run_connector_conformance). The routing constraint ('Routes only through the exact project/account governed connector authority') is a precondition, not usage direction, and no conditions, exclusions, or alternatives are named.

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