start_research_runStart a research run for a project — discovers keywords, evaluates competitors, and writes opportunity clusters. Consumes one credit. Returns { runId }; poll get_research_status for progress. Returns { entitlement } instead when the operator is on the free plan.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses material behaviors beyond the annotations: it consumes one credit, runs asynchronously (requiring polling), and returns a different payload on the free plan. These are non-obvious consequences that affect invocation and expectation management. The description does not contradict the readOnlyHint=false/destructiveHint=true 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?
Three tight sentences with no filler: purpose and effects first, then cost and response contract. Every sentence adds necessary information, and the most decision-relevant detail (what the tool does) is front-loaded.
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 one-parameter asynchronous mutation with no output schema, the description covers the return value ({ runId }), the progress-tracking mechanism, and the free-plan alternate response. Error cases and insufficient-credit behavior are not described, but those are not required for selecting or invoking the tool correctly.
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 zero description coverage, so the description carries the burden of explaining the lone 'id' parameter. 'Start a research run for a project' strongly implies that id is the project identifier. However, it is not stated explicitly as 'id is the project ID,' so the mapping is slightly implicit.
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 action ('Start a research run'), names the resource (a project), and describes what the run does: discovers keywords, evaluates competitors, and writes opportunity clusters. This clearly differentiates it from the many read/status sibling tools by framing it as an initiating action with concrete effects.
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?
It explicitly tells the agent to poll get_research_status for progress after receiving a runId, pointing to the correct follow-up sibling. It also signals that this tool starts work rather than checking status or listing outputs. It does not enumerate when-not alternatives, but the async routing is clear and sufficient for correct use.
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 have distinct purposes, but a few pairs could confuse an agent: add_article_suggestion vs create_article_suggestion_with_input, and get_article_brief vs download_brief_markdown vs get_write_handoff all deal with brief content. The detailed descriptions help disambiguate, but the overlap is real.
All tool names follow a consistent verb_noun pattern in lowercase snake_case (create_project, list_opportunities, generate_article_brief, lint_draft). There is no mixing of camelCase, acronyms, or vague verbs, making the naming predictable and readable.
50 tools is excessive for an MCP server, even for a broad platform like content operations. While the scope is large, this many tools will overwhelm agents and increase latency and context cost. Most practical servers are well under 25.
The tool surface covers the full content lifecycle: project creation, research, opportunity clustering, content planning, briefs, drafting, linting, publishing, and reporting. Minor gaps exist (e.g., no delete_project, no remove_destination, no direct analytics beyond distributions), but they are workarounds or handled in the web UI.