tasks_deleteSoft-delete a task: it moves to the recycle bin for 30 days and can be brought back with tasks_restore. Admin-only. Not permanent, so no confirmation phrase is required - but still tell the user what you removed.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Even though destructiveHint is already true, the description adds critical behavioral detail: the delete is soft, the task goes to the recycle bin for 30 days, restoration is possible, and admin-only authorization applies. It also clarifies that no confirmation phrase is required, which directly informs the agent's interaction behavior. This goes well beyond the 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?
The description is compact, front-loaded with the primary operation, and contains only high-value details: soft-delete behavior, restore path, admin-only restriction, and the required user notification. No redundant filler is present.
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 one-parameter tool with no output schema, the description covers the key facts an agent needs: what happens, who can use it, how long it lasts, how to undo it, and what to tell the user. Nothing essential is missing for correct invocation and interaction.
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?
The schema has 0% description coverage for task_id, and the description does not explain the parameter beyond referring to 'a task.' The field name is fairly self-explanatory, but at this coverage level the description should at least confirm that task_id identifies the task to be deleted, or specify any expected format. It does not compensate for the missing schema documentation.
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-resource combination: 'soft-delete a task.' It further distinguishes this tool from tasks_restore by noting the task can be brought back, and from a permanent delete by mentioning the 30-day recycle bin. This makes the tool's purpose unambiguous even among many sibling delete tools.
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 gives clear context: it is admin-only, the delete is soft, and the task can be restored via tasks_restore. It also provides the user-facing communication requirement. It does not explicitly enumerate when not to use it versus other delete tools, but the soft-delete versus restore distinction is strong enough to guide selection.
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.
Most tools follow a clear resource+action pattern and the descriptions are unusually precise about boundaries. A few near-overlaps remain: projects_get_finance vs projects_get_financials, and notes_create vs crm_log_activity on a deal are both plausible for recording a note on a deal.
The domain_prefix_action convention is consistent across nearly all tools, e.g. crm_create_lead, projects_update_risk, timelog_approve_time. Deviations include standalone list_trash, meta tools like whoami/tool_search/tool_invoke, and the confusing projects_get_finance/projects_get_financials pair.
With 105 tools, this far exceeds the 50+ threshold defined as an extreme mismatch. Even for a full ERP/CRM suite, the fine-grained split—39 project tools alone—creates a massive tool-selection surface that is hard for an agent to navigate reliably.
The surface covers CRM, projects, tasks, time/expenses, HR, notes, notifications, contracts, and reporting with create/read/update/delete for most primary entities. Minor gaps exist: crm_log_activity has no read-back path, contracts lack delete/restore, and proposals are intentionally read-only, but agents can work around these.