agent_run_followupSend a follow-up to an existing Cursor cloud agent (re-injects TeamShared MCP).
| Name | Required | Description | Default |
|---|---|---|---|
| agent | No | Override agent attribution label | |
| prompt | Yes | Follow-up prompt for an existing cloud agent | |
| run_id | No | TeamShared run UUID or Cursor run-… id | |
| cursor_agent_id | No | Cursor bc-… id when run_id is omitted |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose a non-obvious behavior: that the follow-up re-injects TeamShared MCP into the agent. But it does not describe side effects, permission requirements, or what happens to the existing run, leaving the agent to infer the operational impact.
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 a single front-loaded sentence with no filler. It communicates the primary action and one behavioral detail efficiently. The parenthetical is cryptic but compact, and the overall length is appropriate for a tool whose parameter semantics are already covered by the schema.
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 that the schema documents all four parameters and an output schema exists, the description does not need to explain return values or parameter formats. It is minimally adequate, but it lacks explicit guidance on how run_id and cursor_agent_id relate to the 'existing' agent and does not clarify what happens when both are omitted. No annotations exist to compensate for these gaps.
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%, so the parameters are already well-documented in the input schema. The description itself adds no semantic detail beyond the schema, which is acceptable given the high schema coverage. There is no contradiction or missing parameter meaning that the description should have compensated for.
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 verb and resource: 'Send a follow-up to an existing Cursor cloud agent.' It distinguishes itself from sibling tools like agent_run_start or agent_run_status by targeting an existing run rather than starting/listening to one. The parenthetical '(re-injects TeamShared MCP)' adds context but is jargon-heavy and slightly obscures the core purpose.
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 phrase 'existing Cursor cloud agent' implies this tool is for continuing or prompting an already-running agent, which provides some usage context. However, it never explicitly names alternatives like agent_run_start or states when not to use this tool. The selection guidance is left to inference rather than stated directly.
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 104 tools across many domains (memory, work, projects, files, agents, context, strategic, ontology), the use of clear prefixes (memory_, work_, project_, file_, agent_run_, context_) makes most tools distinct. However, there are some potential confusions between memory_session_* vs memory_state_*, and memory_recall vs memory_think vs memory_assemble_context, though descriptions clarify their specific purposes. Aliases like memory_playbook_get for memory_procedure_get are explicit and reduce ambiguity.
Tool names follow a highly consistent pattern: prefix_domain_action (e.g., file_create, work_update, memory_recall, agent_run_start). All use snake_case, with verbs consistently placed after the domain prefix. Even less common tools like account_brief and attention_snapshot fit the overall naming scheme, making the set predictable and easy to navigate.
At 104 tools, this is an exceptionally large surface area, far exceeding the 25+ threshold that feels heavy. However, the server covers an extensive domain (organizational memory, work management, project tracking, file sharing, agent orchestration, and strategic planning), which justifies a large count. Still, the sheer number may overwhelm agents, and some tools could be consolidated (e.g., many memory_session_* and memory_state_* variants).
The tool surface is remarkably complete for its stated purpose, covering CRUD operations for files, work items, projects, and memory, plus lifecycle management for agents, sessions, and strategic plans. Minor gaps exist (e.g., no direct memory_item_get by ID, no section removal in projects), but agents can work around these using existing tools like memory_recall or work_create with parent_id. Overall, the set minimizes dead ends.