Skip to main content
Glama
agentisend

agentisend

List connections

list_oauth_grants
Read-onlyIdempotent

Lists the assistants connected to an account and shows when each last used its connection, helping users review and audit active OAuth grants.

Instructions

Purpose: see which assistants are connected to this account, and when they last used the connection. NOT for: an assistant acting on its own. This is a person’s list. A key is refused with human_action_required. Returns: data, has_more, and next_cursor. Each row has id, client_id, client_name, scopes, created_at and last_used_at.

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": "list_oauth_grants"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoPage size (1-100).
cursorNonext_cursor from the previous page. Omit for the first page.

Output Schema

NameRequiredDescriptionDefault
dataNoThis page of rows.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
has_moreNoTrue when another page follows.
next_cursorNoPass back as cursor for the next page; null on the last page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the authorization rule that key-based calls are refused with human_action_required, a behavioral trait not captured by the annotations.

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?

It is structured into labeled Purpose / NOT for / Returns lines with the core intent front-loaded and no filler. Every sentence carries information for the caller.

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 paginated read-only listing tool with a full output schema, the description covers purpose, the caller restriction, and pagination fields adequately. Nothing an agent needs to invoke it correctly is missing, and the return detail, while partly redundant with the output schema, does no harm.

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 limit and cursor are documented in the schema itself. The description references next_cursor only in the context of the return shape, adding no syntax or semantics beyond what the schema already provides, so the baseline of 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?

The description gives a specific verb and resource ('see which assistants are connected to this account, and when they last used the connection'), which is far more informative than the generic title 'List connections'. It is distinguishable from siblings like revoke_oauth_grant because it is explicitly a read/list operation rather than a mutation.

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?

It provides an explicit 'NOT for' clause: an assistant acting on its own, since 'A key is refused with human_action_required.' This is a clear when-not condition tied to the caller's identity. It stops short of naming the sibling alternative (revoke_oauth_grant) for the revoke case, so it is not fully exhaustive.

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