Bloom

Review connection access

request_access

Request browser review of this connection, including additional projects, whole workspaces or OAuth scopes. Returns an approval URL; never grants access itself. Show the URL to the user; only the account owner can approve. Approved projects and workspaces apply to this OAuth connection immediately: retry after the user approves. A newly approved OAuth scope is signed into new credentials (reconnectRequired): the MCP host's re-authenticate action gets them, its consent page asks only for the added scopes, and nothing needs removing. A call that needs a scope this connection lacks answers 403 insufficient_scope, which hosts with OAuth step-up turn into that re-authentication themselves. API-key connections return key-management instructions. Cancel leaves existing access unchanged. Your tool list shows only what this connection's scopes and your roles allow: a tool or guide section you need but do not see is one more scope or role away, so request it here.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "request_access"
  }
}

Input Schema

Name	Required	Description	Default
`scopes`	No	Additional OAuth scopes to request. Approval requires the account owner, followed by reconnecting the client.
`projectIds`	No	Additional projects to request. These are unchecked review hints; only the account owner can approve access.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the mutation profile; the description supplies the full lifecycle: an approval URL is returned, only the account owner can approve, approval takes effect immediately for projects/workspaces, scopes land in new credentials via reconnectRequired, API-key connections get key-management instructions instead, and cancelling leaves existing access unchanged. No claim conflicts with readOnlyHint=false or destructiveHint=false.

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?

The core contract (returns URL, grants nothing, owner approves, then retry) is front-loaded in the first three sentences. The later prose is dense and occasionally clause-heavy, but nearly every sentence carries distinct operational information rather than restating the schema.

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?

With no output schema, the description correctly takes on return-value explanation: the approval URL, the 403 insufficient_scope response, reconnectRequired on new credentials, and key-management instructions for API-key connections. An agent has everything needed to call it and to interpret the outcome.

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 already 100%, yet the description adds real meaning: projectIds are "unchecked review hints" rather than binding grants, while approved scopes require owner approval plus client reconnection. It stops short of scope syntax or ID formats, which the schema already covers.

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 and resource: "Request browser review of this connection, including additional projects, whole workspaces or OAuth scopes." It also immediately clarifies what it is not ("never grants access itself"), which separates it from any sibling that would mutate access directly.

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

Usage Guidelines5/5

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

Gives explicit when-to-use guidance ("a tool or guide section you need but do not see is one more scope or role away, so request it here"), the follow-up action ("retry after the user approves"), and the alternative path for hosts with OAuth step-up that translate 403 into re-authentication themselves.

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

All Bloom tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?