Skip to main content
Glama

agentView

by de.agentview
OverviewDiscussionsAdmin

Create Auth Session

create_auth_session

Starts a browser login and returns a loginUrl plus sessionRequestId. Use as STEP 0 in a fresh conversation before any protected tool. Show the loginUrl to the user as a clickable link in their language, then poll get_auth_session until 'active' and pass session_request_id on every later call. Returns sessionRequestId, loginUrl, pollUrl and expiresIn.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeNoRequested access scope: 'content_only' (read and send content), 'display_setup' (content plus connecting or creating screens; use it when the user has no screen yet) or 'admin' (everything, incl. rename, delete, rebind). Defaults to 'content_only'.
agent_identifierNoOptional display name of the MCP client or agent, shown to the user in the browser consent screen. Example: 'ChatGPT' or 'my-home-automation'.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNo
pollUrlNo
loginUrlNo
expiresInNo
requestedScopeNo
sessionRequestIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / scope / description
      Previous value: -"Requested access scope. Must be either 'content_only' (read and send content to displays) or 'admin' (content_only plus create/delete/rename displays). Defaults to 'content_only'."New value: +"Requested access scope: 'content_only' (read and send content), 'display_setup' (content plus connecting or creating screens; use it when the user has no screen yet) or 'admin' (everything, incl. rename, delete, rebind). Defaults to 'content_only'."
    • changedInput schema / properties / scope / enum
      Previous value: -[
-  "content_only",
-  "admin"
-]New value: +[
+  "content_only",
+  "display_setup",
+  "admin"
+]
  2. Changed6 schema fields changed
    • changedOutput schema / properties / expiresIn / type
      Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]
    • changedOutput schema / properties / hint / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedOutput schema / properties / loginUrl / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedOutput schema / properties / pollUrl / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedOutput schema / properties / requestedScope / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedOutput schema / properties / sessionRequestId / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
  3. Changed6 schema fields changed
    • removedInput schema / properties / agent_identifier / default
      Removed value: -null
    • changedInput schema / properties / agent_identifier / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • removedInput schema / properties / scope / default
      Removed value: -null
    • addedInput schema / properties / scope / enum
      Added value: +[
+  "content_only",
+  "admin"
+]
    • changedInput schema / properties / scope / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "expiresIn": {
+      "type": "integer"
+    },
+    "hint": {
+      "type": "string"
+    },
+    "loginUrl": {
+      "type": "string"
+    },
+    "pollUrl": {
+      "type": "string"
+    },
+    "requestedScope": {
+      "type": "string"
+    },
+    "sessionRequestId": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations cover only the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds real behavioral context beyond that: the tool is stateful, yields a loginUrl requiring user action, produces a session that is polled to 'active', and expires (expiresIn). It stops short of saying what happens on expiry or whether sessions can be reused, so not a 5.

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?

Front-loaded with the operation and its return values, then the workflow. Sentences are dense but nearly all carry actionable content. The final sentence listing 'sessionRequestId, loginUrl, pollUrl and expiresIn' is largely redundant given the output schema exists, which is the only real waste.

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 multi-step auth bootstrap, the description supplies the full lifecycle (initiate → show link → poll → pass session_request_id onward) and the output schema handles return shapes. Nothing an agent needs to call this correctly is missing.

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% and both parameters (scope enum, agent_identifier) are fully documented in the schema, including the enum semantics and default. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

Specific verb+resource: 'Starts a browser login and returns a loginUrl plus sessionRequestId.' It clearly distinguishes itself from the sibling get_auth_session by describing the initiate-vs-poll split, so an agent can route between them without opening either schema.

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?

Explicit when-to-use ('STEP 0 in a fresh conversation before any protected tool'), an explicit alternative ('poll get_auth_session until active'), and a downstream obligation ('pass session_request_id on every later call'). This is close to ideal routing guidance for a session-bootstrap tool.

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

All agentView toolsInspect
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