run_agentRun one of your agents once and return what every step did, in order, with what it returned and how long it took. Pass its declared inputs as an object keyed by their key from describe_agent. Steps that reach a paid vendor are counted against your live-sweep allowance, one each.
| Name | Required | Description | Default |
|---|---|---|---|
| inputs | No | The agent's declared inputs, keyed by `key`. Values are strings. | |
| agent_id | Yes | From list_agents. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does well by explaining the sequence and content of the return value ('what every step did, in order, with what it returned and how long it took') and by disclosing that paid-vendor steps consume allowance. It could mention potential real-world side effects of running an agent, but the provided details are substantial beyond the bare schema.
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?
Three dense sentences, each earning its place: the first defines the behavior and output, the second tells the agent how to structure invocation, and the third discloses the cost implication. No filler or repetition.
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 two-parameter tool with no output schema, the description covers the high-level return shape, the input construction method, and a key consumer warning. It is almost complete, but lacks an explicit statement of what happens on failure or whether the run is synchronous, which would make it fully self-sufficient.
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 the baseline is 3. The description adds meaningful semantics for the inputs parameter by stating it must be an object keyed by the `key` values from describe_agent, which goes beyond the schema's generic 'keyed by key'. It does not add much about agent_id, but the schema already covers it with 'From list_agents.'
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 the verb 'Run', the resource 'one of your agents', and the singular execution mode 'once'. It is immediately distinct from siblings like describe_agent, list_agents, and draft_pitch because it describes executing an agent and reporting the step-by-step results.
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 provides a concrete usage pointer: pass inputs keyed by their `key` from describe_agent, implying that describe_agent should be consulted first. It also flags a cost-related condition for paid vendor steps. It does not explicitly list when not to use the tool or name an alternative, but the execution purpose is clear enough in context.
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.
Each tool targets a distinct resource or action: agents, documents, prospects, competitors, visibility, and link checks are clearly separated. Even the closely related link-building tools are differentiated by whether they find prospects, find competitor gaps, or verify existing links.
Almost every tool follows a clear verb_noun pattern using lowercase snake_case, such as list_agents, run_agent, and verify_links. The one minor deviation is backlink_gap, which reads as a noun phrase rather than an imperative verb, so the pattern is not perfect.
Fourteen tools is within the ideal range and each tool covers a meaningful part of the Mentionry workflow. The count feels justified given the breadth of features: site analysis, competitor discovery, prospecting, link verification, outreach drafting, agent management, document retrieval, and visibility reporting.
The core workflow is well covered: audit a site, find competitors, discover prospects, verify links, draft outreach, run agents, and read results. The main gaps are agent lifecycle management and document management beyond reading, but those may reasonably live in the Mentionry dashboard rather than the MCP surface.