get_outreach_approval| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | No | The agent whose effective settings to read. When omitted, reads the current agent's settings if this chat is tied to one, otherwise the account-wide settings. | |
| on_behalf_of | No | An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account. |
Changes observed during successful MCP inspections.
Input schema / properties / on_behalf_ofAdded value: +{
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "An agency client's email, from list_agency_clients, to run this call in that client's account: their agents, settings, connected accounts, and credits. Omit it to act on your own account."
+}Input schema / properties / agent_idAdded value: +{
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "The agent whose effective settings to read. When omitted, reads the current\nagent's settings if this chat is tied to one, otherwise the account-wide settings."
+}Input schema / properties / task_idRemoved value: -{
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "default": null,
- "description": "The agent (task) whose effective settings to read. When omitted, reads the current\nagent's settings if this chat is tied to one, otherwise the account-wide settings."
-}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only supply readOnlyHint=true; the description adds substantial context the annotation cannot: the meaning of `pending_approval`, the override-vs-account-default resolution, and the per-subtype keying semantics. It even documents the return shape, which matters since no output schema exists.
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?
Front-loaded with the core purpose, then the diagnostic use case, then scope. The XML-style summary/returns sections are slightly verbose in structure but each sentence carries information, so little is wasted.
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?
Despite the absence of an output schema, the description documents the returned dict keys (`settings`, `override_active`, `account_settings`) and their true/false semantics. Combined with full parameter coverage, an agent has everything needed to call and interpret this read.
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 100%, and the description's scope explanation for agent_id largely restates what the schema already says ('reads the current agent's settings if this chat is tied to one, otherwise the account-wide settings'). It adds the override nuance for the resolved scope but does not introduce new syntax or format detail beyond the schema baseline.
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?
States a specific verb (read) and resource (per-subtype outreach approval settings) and explains what the settings decide: auto-send vs wait for approval. It is clearly distinguishable from the mutating sibling set_outreach_approval.
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?
Gives explicit when-to-use guidance: read this before telling a user a send looks stuck, because a message in `pending_approval` is a normal gated state rather than a failure. It also states the scope-selection conditions for passing vs omitting agent_id.
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.