FindAgent

findagent_edit_department

Idempotent

Edit the settings of YOUR OWN department — its reporting instructions, name, and description. report_instructions is the department's behavioural lever: it is prepended to EVERY member's (and the orchestrator's) prompt on every run, and to every prompt-template tool result on a direct <alias>__<tool> call, so it is how you tell the whole team how to work and how to report, without editing any member agent. Pass the department slug plus only the fields you want to change; pass an empty string to CLEAR report_instructions or description. This does NOT change the department's composition — members, topology, orchestration and flow hints are edited in the department builder on the web. It is also how you UNDO a deletion: an archived department is put back with status:"draft" (on its own, then edit it in a second call). Works on a PERSONAL department you own, and on an ORG department when you are that organization's owner or admin — an org department is reached by its slug, and an ordinary org member cannot edit one. Call findagent_list_my_agents to see the personal departments you own.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	New department name (3–80 chars).
`status`	No	Pass "draft" to RESTORE a department you archived (deleted): it becomes a draft again and serves its connector, runs and schedules exactly as before, with its members and report_instructions untouched. Send it ALONE — restore first, then edit in a second call. "draft" is the only value: a department is never published.
`department`	Yes	The slug of a department you own (from findagent_list_my_agents).
`description`	No	New description (10–2000 chars). Pass an empty string to remove it.
`report_instructions`	No	Standing instructions prepended to every member's and the orchestrator's prompt on every run, and to every prompt-template tool result on a direct <alias>__<tool> call — e.g. how to report, what to prioritise, what house style to use. Pass an empty string to remove it. Checked on save against a prompt-injection deny-list and scanned for leaked secrets; the save is rejected on a hit.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`slug`	No
`status`	No
`restored`	No
`instructions`	No
`report_instructions_set`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 26, 2026

changedInput schema / properties / report_instructions / description

Previous value: -"Standing instructions prepended to every member's and the orchestrator's prompt at run time — e.g. how to report, what to prioritise, what house style to use. Pass an empty string to remove it. Checked on save against a prompt-injection deny-list and scanned for leaked secrets; the save is rejected on a hit."New value: +"Standing instructions prepended to every member's and the orchestrator's prompt on every run, and to every prompt-template tool result on a direct <alias>__<tool> call — e.g. how to report, what to prioritise, what house style to use. Pass an empty string to remove it. Checked on save against a prompt-injection deny-list and scanned for leaked secrets; the save is rejected on a hit."

addedInput schema / properties / status

Added value: +{
+  "description": "Pass \"draft\" to RESTORE a department you archived (deleted): it becomes a draft again and serves its connector, runs and schedules exactly as before, with its members and report_instructions untouched. Send it ALONE — restore first, then edit in a second call. \"draft\" is the only value: a department is never published.",
+  "enum": [
+    "draft"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / restored
```
Added value: +{
+  "type": "boolean"
+}
```

AddedSep 15, 2026

TDQS

A5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description adds substantial unstated behavior: report_instructions is prepended to every member's/orchestrator's prompt and templated results, empty strings clear fields, saves are rejected on injection/secret scans, and archived departments are restored as drafts. No contradictions 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence names the operation and fields, and subsequent sentences add high-value caveats (no composition changes, restore flow, permission boundary, security check) without redundancy. Dense but appropriately sized for a tool with this many behavioral details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with 5 params, permissions, restore semantics, security checks, and an output schema, the description covers all necessary call-time knowledge: scope of edits, permission model, field semantics, restoration workflow, and where to get department slugs. The output schema covers return-shape needs, so nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already covers all five parameters at 100% coverage, so the baseline is 3, but the description goes beyond: it explains the operational meaning of report_instructions, the clearing semantics of empty strings, the 'send status alone' restore rule, and the source of valid department slugs. This materially helps an agent choose and format values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb (Edit) and resource ('settings of YOUR OWN department'), enumerates the exact fields (reporting instructions, name, description), and explicitly separates itself from composition editing done in the web builder. This differentiates it from sibling edit tools such as edit_metadata and edit_price.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit conditions: personal departments owned by caller, org departments restricted to owner/admin; explains when not to use it (composition changes go to web builder) and directs users to list_my_agents to discover departments. It also prescribes the restore workflow (status alone first, then edit) rather than leaving sequencing ambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FindAgent tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?