Skip to main content
Glama

ToolRouter

by io.github.Humanleap

Connector Permissions

connector_permissions

View or set permissions for tools on a connected MCP server — which tools are allowed, rate limits, budget caps, argument restrictions. Pass the connector slug (from connector_list) and action: "list" to see current rules, or action: "set" with tool_name + rules to update one. Team scope requires admin role.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
slugYesConnector slug.
actionNoOmit to list permissions for all tools. Pass "set" with tool_name + rules to update one.
allowedNoWhether the tool is allowed (for set).
billingNoScope: "personal", "team" (auto-resolves if on one team), a team slug, or "team:<id>".
tool_nameNoTool name (for set). Use "*" for all tools on this connector.
cost_per_callNoCost in millicents per call (for set).
budget_per_dayNoMax daily spend per user, in millicents (for set).
nl_filter_modeNoHow to enforce NL rules: strict (block on violation) or advisory (log only). Default: strict.
arg_schema_rulesNoJSON Schema validating tool arguments (for set). Example: {"properties":{"channel":{"enum":["#general"]}}}
rate_limit_per_dayNoMax calls per day, per user (for set).
rate_limit_per_hourNoMax calls per hour, per user (for set).
team_budget_per_dayNoMax daily spend team-wide, in millicents (for set).
team_rate_limit_per_dayNoMax calls per day, team-wide (for set).
team_rate_limit_per_hourNoMax calls per hour, team-wide (for set).
arg_natural_language_rulesNoPlain English rules for argument filtering (for set). Example: "Only allow queries for the last 90 days."

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only state the tool is not read-only, not open-world, not idempotent, and not destructive. The description adds useful behavioral context: 'set' updates one tool's rules, 'list' shows current rules, and team scope requires admin role. It does not detail all side effects of mutation (e.g., immediate enforcement or overwrite semantics), but it goes beyond what annotations convey.

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

Conciseness5/5

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

Three sentences with strong front-loading: the opening sentence summarizes the tool's purpose and scope, the second explains the two invocation modes, and the third flags the admin precondition. No filler, every sentence earns its place.

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

Completeness4/5

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

Given the tool's complexity (15 parameters) and absence of an output schema, the description covers the essential workflow: how to list, how to set, where to get the slug, and an important access constraint. It doesn't describe the shape of the 'list' response, but that is an acceptable gap when parameters are fully documented in the schema.

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

Parameters3/5

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

Schema description coverage is 100%, with detailed descriptions for all 15 parameters, so the description correctly does not restate each parameter. It adds marginal workflow context (pass slug, choose action) that is partially redundant with the schema's own action description. This is an adequate but not exceptional supplementation.

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?

The description clearly states a specific verb-resource pair: view or set permissions for tools on a connected MCP server. It enumerates the permission dimensions (allowed tools, rate limits, budget caps, argument restrictions) and positions the tool relative to connector_list by mentioning the connector slug, making its purpose distinct from connector lifecycle siblings.

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?

The description gives explicit when-to-use guidance for the two actions (list vs set) and points to connector_list as the source for the slug. It notes the admin role requirement for team scope. It does not explicitly name alternative tools to use instead, but the action breakdown and prerequisite reference provide clear operational guidance.

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

All ToolRouter toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

Tools are grouped by clear resource prefixes (account_, brain_, connector_, credential_, file_, job_, key_), and most actions have distinct purposes. A few boundaries overlap—brain_admin's lint action duplicates brain_lint, and account_preferences/setup/switch could momentarily confuse—but the descriptions resolve most ambiguity.

Naming Consistency3/5

The dominant pattern is resource_verb for actions (file_read, job_cancel, key_create) and resource_noun for state views (credits_balance, brain_settings, account_preferences), which is readable. However, exceptions like discover, use_tool, top_up_credits, and feedback_request_tool break the pattern, and the set is not consistently verb_noun.

Tool Count2/5

47 tools is well beyond the comfortable range; even though prefixes organize them, the agent faces a large selection surface with many narrowly scoped tools. A more consolidated set with action-based subcommands would be easier to navigate.

Completeness4/5

Core workflows are covered end-to-end: account setup and billing, connector and credential management, file CRUD, job polling, key lifecycle, brain knowledge management, and catalogue discovery/execution. Gaps are minor—outfit/persona/product/scene are list-only, connectors lack an update operation, and there is no explicit single-page brain get—but agents can generally work around them.

Resources