Remove a decision by its reference so it can be restored later. Requires task-change permission and a stated reason.
Delete a decision by ref. Its number is never reused and fenbs_restore_decision brings it back with its deciders, links and versions. Say why before you do it. Needs permission to change tasks.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it discloses several non-obvious traits: the decision number is never reused, deletion is restorable via a sibling (implying a soft delete), and elevated permissions are required. It stops short of stating whether links/versions are immediately detached or how long restore remains available.
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?
Four short sentences, front-loaded with the action, then consequences, then the alternative, then prerequisites. Every sentence adds information, though 'Say why before you do it' is vague enough to be a slight drag.
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 destructive, single-parameter tool with no annotations and no output schema, the description covers the essentials: what is destroyed, that it is recoverable, and the permission gate. Missing only restore-window and cascade details, which are minor for this tool's complexity.
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% for the single required 'ref' parameter, so the description must compensate and largely does not — it only repeats 'by ref' without explaining whether ref is an ID, a slug, or the 'number' alluded to later. The agent gets almost no additional resolution on the one input it must supply.
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 with a specific verb+resource pair ('Delete a decision by ref') and immediately differentiates itself from the sibling fenbs_restore_decision, which does the opposite. An agent can distinguish this from get_decision, add_decision, and restore_decision without inspecting any schema.
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?
It names the alternative path explicitly (fenbs_restore_decision brings the decision back) and states a precondition ('Needs permission to change tasks'), which is real routing guidance. However, 'Say why before you do it' is ambiguous — the schema has no reason field and additionalProperties is false, so it is unclear whether this is a workflow convention or a hard requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.