onedrive_write_fileWrites text content to a file in OneDrive. Overwriting an existing file keeps its previous version first, in LMCP's own folder, and the answer says where (previous_version).
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Absolute path to the file in OneDrive | |
| confirm | No | Ignored; kept for older clients. | |
| content | Yes | Text content to write |
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | ||
| bytes | Yes | ||
| written | Yes |
Changes observed during successful MCP inspections.
Input schema / properties / confirm / descriptionPrevious value: -"Required (true) to OVERWRITE an existing file. Not needed to create a new file."New value: +"Ignored; kept for older clients."Input schema / properties / confirm / descriptionPrevious value: -"Must be true to write"New value: +"Required (true) to OVERWRITE an existing file. Not needed to create a new file."Input schema / properties / confirm / descriptionPrevious value: -"Required (true) to OVERWRITE an existing file. Not needed to create a new file."New value: +"Must be true to write"Input schema / properties / confirm / descriptionPrevious value: -"Must be true to write"New value: +"Required (true) to OVERWRITE an existing file. Not needed to create a new file."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true; the description goes beyond that by explaining exactly what is destructive about it — an existing file is overwritten, with its prior contents preserved as a version in LMCP's own folder, and the response reports where. It leaves out auth/permission requirements and whether the version is retained indefinitely.
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 short sentences, front-loaded with the core action, and the second sentence carries only the non-obvious overwrite/version semantics. Nothing is repeated from the schema or annotations.
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?
An output schema exists, so the description need not explain return values, and it still helpfully names `previous_version`. For a destructive write operation it covers the key risk; only permission/scope requirements are 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 path, content, and the deprecated confirm flag are already documented in the schema. The description only reinforces that content is text and that overwriting an existing file produces a `previous_version` in the response, which adds a little but not much 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 and resource — writes text content to a OneDrive file — which is enough to distinguish it from sibling readers (onedrive_read_file) and non-OneDrive writers (file_write, gdrive_write_file). It does not call out the sibling boundaries explicitly, so it stops just short of a 5.
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?
Usage is implied by the name and by the overwrite clause, but there is no explicit guidance on when to prefer this over file_write, gdrive_write_file, or onedrive_move_file, nor any stated preconditions. For a write tool with several near-neighbours, that is a real gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.