Share a OneDrive file as a link

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

Annotations declare non-destructive, idempotent, open-world, but the description adds crucial context the annotations cannot: an anonymous edit link effectively grants write/delete access to anyone holding it and requires confirm:true, reuse behavior means the same link type may come back rather than a new one, the tool costs 0 credits, and OneDrive connection is required. That is substantive behavioral disclosure, not restatement.

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?

Dense but front-loaded: the core action and the confirm gate come early, then supporting detail on scope/type constraints. The long parentheticals (iframe, subscription refusal wording) are informative but make it a heavy single paragraph.

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?

No output schema exists, yet the description tells the agent where to verify results (the item's permission list) and that the reply indicates reuse. Auth prerequisite, credit cost, safety gate, and per-enum constraints are all covered; nothing needed for a correct call is missing.

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 coverage is 100%, so the baseline would be 3, but the description adds real meaning: embed produces an <iframe> link and is personal-only, password and expiresAt both require a Microsoft 365 subscription on personal accounts, and the failure message is described. confirm's blast radius (anonymous edit lets anyone change or delete) is spelled out beyond the terse schema text.

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?

Opens with a specific verb and resource (create a sharing link to a OneDrive file or folder) and even names where fileId comes from (list_onedrive_files). An agent can immediately distinguish this from update_onedrive_file, get_onedrive_file, and onedrive_file_permissions.

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?

States defaults for both enums, names the conditions under which each option applies (embed = personal OneDrive only, organization = work/school only, users = invited people only), and gives an explicit gating rule for confirm:true on anonymous edit links. It also points to the permission list for verification, and the sibling onedrive_file_permissions covers the read side.

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