invoke_agentInvoke a specific AI agent with given inputs.
The agent will execute within policy constraints and return structured output. All agent runs are logged for audit and traceability.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | Agent-specific input parameters | |
| agentId | Yes | Agent to invoke | |
| context | No | Additional context (brand voice ID, date range, etc.) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate the tool is not read-only, not destructive, and open-world, but the description adds valuable context: the agent executes under policy constraints and returns structured output. It also discloses that all runs are logged for audit and traceability. This goes beyond annotations without contradicting them, though it stops short of describing possible side effects.
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 three sentences with front-loaded purpose and no redundant words. Each sentence contributes: invocation, behavior, and logging. It is concise and appropriately structured for an agent-invocation tool.
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 the tool's complexity (12 agents, nested input objects, no output schema), the description covers essential context: policy constraints, structured output, and audit logging. It does not detail how to select an agent or what output to expect, but the schema enumerates agent IDs, and 'structured output' is a reasonable generic promise. The absence of agent-specific behavioral details is a minor gap, not a critical one.
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 input schema provides 100% coverage with descriptions for every parameter: agentId, input, and context. The description offers no additional parameter-specific meaning, so it stays at the baseline of 3. The phrase 'given inputs' adds nothing beyond the schema's 'Agent-specific input parameters.'
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 uses a specific verb and resource: 'Invoke a specific AI agent with given inputs.' It clearly distinguishes this from sibling tools like list_agents and get_agent_run, which are about listing or retrieving rather than executing. The mention of execution within policy constraints and structured output further clarifies the action.
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 implies the tool is for invoking an agent but provides no explicit when-to-use guidance or alternatives. It does not mention that list_agents could be used to discover available agent IDs or get_agent_run to fetch results, so usage context is only implicit from the tool name and schema.
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.
With 148 tools, there is significant overlap. For example, generate_content, publish_ai, generate_post_bundle, and request_project_content all generate content; get_analytics, get_unified_analytics, get_post_analytics, get_ad_performance, and get_unified_ad_report all fetch performance metrics; and list_inbox vs list_conversations blur comment and conversation management. Descriptions help, but boundaries between tools are often unclear.
Most tools follow a verb_noun pattern (e.g., list_teams, create_goal, delete_post), but there are notable deviations: create_library_item vs save_to_library, publish_content vs publish_ai, schedule_content vs schedule_content_advanced, and connect_platform vs connect_connector. Mixed prefixes like 'autopilot_', 'check_', and 'get_' are fine, but overlapping verbs and a hyphen in 'connect_linkedin-page' reduce consistency.
148 tools is extreme for any server. Even for a broad social media management platform, this is far beyond what an agent can effectively navigate. The count is unwieldy and suggests the surface should be split into multiple focused servers (publishing, analytics, connectors, workflows, etc.).
The core social publishing workflow is well covered (create, schedule, publish, edit, delete, retry), and there are extensive features for analytics, workflows, connectors, and AI agents. However, some resources have CRUD gaps: no update/delete for brand voices, no delete_project, no update/delete for Product Hunt goals, and no explicit get_workflow. These are workable but notable omissions.