start_retrospectiveMUTATES Parabol data: start a new retrospective meeting for a team (returns the new meetingId). Required: teamId. Optionally name it. Parabol GraphQL: startRetrospective → union. Requires MEETINGS_WRITE.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Optional meeting name. | |
| teamId | Yes | The team id to run the retro for (required). |
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?
The description explicitly says 'MUTATES Parabol data' and mentions the required MEETINGS_WRITE permission, adding meaningful behavior beyond the destructiveHint annotation. It also notes the return value (new meetingId), which helps an agent understand the tool's side effects, though it does not mention potential failure modes.
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 compact and front-loaded with the MUTATES flag, followed by the core purpose and return value. The 'Parabol GraphQL: startRetrospective → union' detail is somewhat technical but brief, and the rest of the content is efficiently organized.
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?
With no output schema, the description compensates by stating that the new meetingId is returned. It covers required parameters, optional naming, permission requirements, and the mutating nature. It could be more complete about the union response variants or failure cases, but it is sufficient for a simple two-parameter tool.
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 baseline is 3. The description mostly restates the schema by saying teamId is required and name is optional, and adds no deeper semantics about formats, defaults, or constraints beyond what the schema already provides.
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 tool starts a new retrospective meeting for a team and returns the new meetingId, which is a specific verb+resource. It does not explicitly compare against sibling start_checkin or start_team_prompt, but the retrospective focus and GraphQL mutation name are enough to distinguish it in practice.
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 provides clear context for when to use the tool: starting a retrospective requires a teamId, optionally a name, and MEETINGS_WRITE permission. It does not explicitly state exclusions or when to prefer a sibling, but the required input and mutation nature make the intended use unambiguous.
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.
Every tool targets a distinct resource and action: get_/list_ tools are clearly separate read paths, create_/update_/start_/add_ tools map to distinct mutations, and the two escape hatches are explicitly labeled. Even near neighbors like list_meetings and list_active_meetings are unambiguous.
Most tools follow a consistent pattern: list_/get_ for reads, create_/update_/start_ for mutations, with plural nouns for collections and singular for single resources. Minor deviations like add_comment, invite_to_team, and the parabol_* escape hatches prevent a perfect score.
With 21 tools, the server sits in the 16-25 range that feels heavy for an MCP surface. The breadth is somewhat justified because Parabol spans organizations, teams, meetings, tasks, and comments, but many tools are list/get variants of the same core entities.
Core read and write flows exist for teams, organizations, meetings, tasks, and comments, but there are notable lifecycle gaps such as no delete_task, no reflection update/delete, and no meeting end/update mutations. The parabol_graphql and parabol_query escape hatches help work around these gaps but do not make the curated surface fully complete.