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

Adds substantial context beyond annotations: the recipient is NOT emailed, no anonymous-link mode exists, non-Microsoft accounts cannot be granted access, a link is returned, and user confirmation is required first. These are exactly the behavioral traits an agent needs and none are inferable from readOnlyHint=false / destructiveHint=false / openWorldHint=true.

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?

Front-loads the action and its result, then uses each following sentence for a distinct non-obvious constraint (named-only, no email sent, confirm first). Bold emphasis is used sparingly on the highest-risk fact; no filler.

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, the description usefully states the return value (a link). Safety is covered by annotations and the behavioral nuances are covered in prose. The remaining gap is the undocumented itemId parameter and the absence of a pointer to list_onedrive_permissions for pre-checking access.

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 80%, so the schema already documents role (with its commenter caveat), email, mailbox, and expiresInDays. The description adds no parameter-level detail — notably itemId is undocumented in both places — so it neither compensates for the gap nor adds meaning beyond the schema.

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?

States a specific verb (give access / share), resource (OneDrive file or folder), actor (a named person by email), and outcome (returns a link to pass on). The OneDrive scoping distinguishes it from share_gdrive_item, and the 'give access' framing distinguishes it from unshare_onedrive_item.

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?

Clearly frames the context (named-person sharing) and rules out the alternative model ('there is no "anyone with the link" option'), plus a workflow prerequisite ('Ask the user to confirm before sharing anything'). It does not explicitly name sibling tools like unshare_onedrive_item or list_onedrive_permissions for checking existing access, so it stops short of full routing guidance.

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