Skip to main content
Glama

UpdateProposalReviewers

Destructive

Add or remove requested reviewers on a schema proposal, the same action as the Reviewers menu in GraphOS Studio. While the proposal is open, GraphOS emails each reviewer you add, every time, including someone already requested. Adding to a DRAFT proposal and removing a reviewer send no email. Only a requested reviewer can call ReviewProposal. Both lists take GraphOS user IDs, which GetOrganizationMembers returns. Pass either list or both. Only organization members can be reviewers, and GraphOS returns a ValidationError that names any other ID. The proposal's author cannot be a reviewer. This tool needs the GraphOS sign-in (OAuth) or a personal API key in the x-api-key header. GraphOS checks reviewers against the organization's members, which a graph key cannot read, so the call fails with NOT_ALLOWED_BY_USER_ROLE. The Platform API does not return the list of requested reviewers, so this tool cannot read it back. Check the proposal in GraphOS Studio to see it. Adding a reviewer who is already requested, removing one who is not, or passing neither list still returns the proposal, so a success does not mean anything changed. Remove only the people the user named. Returns the proposal's ID, or an error with a message. Provide the graph ID, the proposal variant name from GetProposal, and the user IDs to add, to remove, or both.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "graphId": "<graphId>",
      "proposalVariant": "<proposalVariant>"
    },
    "name": "UpdateProposalReviewers"
  }
}

Input Schema

NameRequiredDescriptionDefault
graphIdYes
proposalVariantYes
reviewerUserIdsToAddNo
reviewerUserIdsToRemoveNo

Output Schema

NameRequiredDescriptionDefault
dataNo
errorsNo
extensionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: open proposals email every added reviewer each time, DRAFT additions and removals send no email, graph keys fail with NOT_ALLOWED_BY_USER_ROLE, and ValidationError names invalid IDs. It also discloses a critical trap — the call succeeds even when nothing changed (duplicate add, absent removal, or neither list) and the reviewer list cannot be read back.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Information is front-loaded (what it does, then email semantics, then constraints, then auth, then return), which is good for an agent scanning for a decision. It is dense and slightly repetitive — the closing sentence restates the parameters already covered, and the no-op/read-back caveat could be tighter — but most sentences carry non-obvious facts.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter mutation with an output schema, the description covers what an agent needs: inputs and their sources, auth modes and failure mode, email side effects, silent-success semantics, and return value. The one thing it cannot explain (the reviewer list) is explicitly attributed to an API limitation with a pointer to Studio.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the whole burden and mostly does: graphId and proposalVariant (from GetProposal) are identified, both reviewer lists are explained as user IDs sourced from GetOrganizationMembers, and optionality of each list is stated. It does not clarify null-versus-empty-array semantics for the two optional lists, which is the remaining gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb pair and resource (add/remove requested reviewers on a schema proposal) and anchors it to a known surface (the Reviewers menu in GraphOS Studio). It also implicitly separates this from ReviewProposal by noting that only a requested reviewer can call that one, so an agent can tell the two apart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong context: pass either list or both, obtain IDs from GetOrganizationMembers, only org members can be reviewers, and the author cannot be one. It stops short of an explicit 'use X instead when...' statement versus sibling mutation tools like UpdateProposalStatus or UpdateProposalTitle, so it is clear on context but not on alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources