kaiten_delete_fileDelete an attachment from a Kaiten card by providing the file ID and card ID. Removes the file cleanly, and re-deleting an already-removed file returns success silently.
Remove an attachment. fileId and cardId come from kaiten_list_files. Re-delete of an already-deleted file returns success silently (Kaiten side is idempotent).
| Name | Required | Description | Default |
|---|---|---|---|
| cardId | Yes | Card ID | |
| fileId | Yes | File ID |
Changes observed during successful MCP inspections.
v0.1.7Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint, idempotentHint, and readOnlyHint=false, so the description's main burden is behavioral nuance. It adds valuable context by disclosing that re-deleting an already-deleted file 'returns success silently (Kaiten side is idempotent)', which tells the agent it need not treat a repeat delete as an error. No contradiction with annotations.
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?
Three sentences, each earning its place: the action, the parameter provenance, and the idempotency edge case. The core purpose is front-loaded and there is zero filler or repetition of schema data.
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?
For a simple 2-param delete tool with robust annotations (destructive, idempotent, open-world), the description covers the essentials: the action, where to get IDs, and the re-delete behavior. The only minor gap is that it doesn't describe error behavior for a fileId that doesn't exist on the given card, but the idempotency disclosure mitigates the most likely failure case.
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% and both parameters are well-typed integers with exclusiveMinimum constraints, so the baseline is 3. The description adds genuine value beyond the schema by explaining the provenance of both parameters ('come from kaiten_list_files'), which is the most likely source of agent confusion when calling this tool.
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 states a specific verb ('Remove') and resource ('an attachment'), which clearly differentiates it from sibling tools like kaiten_upload_file and kaiten_list_files. It also tells the agent the exact scope of the operation, leaving no ambiguity about what gets deleted.
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 a clear usage context by stating that 'fileId and cardId come from kaiten_list_files', effectively routing the agent to the prerequisite listing step before deletion. It doesn't explicitly name when-not-to-use alternatives, but the provenance pointer gives enough orientation for a 2-param delete tool amid many siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.