Soft-delete a billing subtask into the recycle bin, where an admin can restore it. Returns a preview unless confirm=true is set.
| Name | Required | Description | Default |
|---|---|---|---|
| confirm | No | Set true to perform the action. Omit or false returns a preview only — nothing is written. | |
| subtask_id | Yes | Id of the subtask to delete. | |
| idempotency_key | No | Optional caller-supplied key; retrying with the same key returns the original result instead of acting twice. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears full burden. It discloses soft-delete nature, admin restoration, preview behavior, and confirm flag effect. It does not cover auth or rate limits, but for a delete tool this is transparent enough.
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 sentences, front-loaded with purpose, no superfluous words. Very concise and well-structured.
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?
Given no output schema, more burden falls on description. It explains the core action and preview, but does not mention the return format of preview, idempotency key behavior details, or the restore counterpart (restore_entity). Adequate but with gaps.
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 baseline is 3. The description does not add new parameter info beyond what the schema's descriptions already provide (e.g., confirm behavior is identical). Thus it meets the baseline but no extra value.
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 clearly states it is a soft-delete operation ('Soft-delete a billing subtask into the recycle bin'), distinguishes itself from permanent deletion (via sibling 'permanent_delete_entity'), and describes the preview behavior. This provides a specific verb+resource with differentiation.
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 explains when to use it (soft-delete) and the preview/confirm behavior, which guides usage. It implicitly contrasts with permanent deletion via sibling tool, but does not explicitly mention alternatives or when not to use.
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.
Multiple tools have overlapping purposes, e.g., create_time_report and log_time both create a single time entry with near-identical descriptions. There are also many similar getter/list tools that blur together, making it hard for an agent to select the right one.
Most tool names use snake_case, but verbs are inconsistent: 'list' vs 'get' for similar operations, 'manage' combines create/update/delete, and 'use_favorite' is an outlier. This pattern reduces predictability.
With 114 tools, the set is extremely large and far beyond a well-scoped server (typical 3-15). This overwhelms agents and suggests many tools could be consolidated or removed.
The tool surface covers a broad domain including customers, projects, tasks, time tracking, invoicing, and user management, but there are gaps like no list_users or direct user listing, and some operations seem redundant rather than filling missing functionality.