Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

My to-do list

connections_todo_list
Read-only

Use this when the member asks what is on their to-do list, what they have to do, their tasks, open items, reminders, follow-ups, what is due or overdue, or whether anything is waiting on them. Returns the member's Connections to-dos across their personal space and every workspace they belong to, the workspace this connection is in first - open items by default, each with its due date, labels and workspace. Answer these questions from THIS list, never from chat history or memory: the list lives here. Not for the assistant's own work log (that is the agent lane, post_agent_todos_list).

Input Schema

NameRequiredDescriptionDefault
labelNoOptional: only items carrying this label/folder.
limitNoMax items to return (1-200, default 50).
queryNoOptional topic filter over titles and labels ('taxes', 'stripe onboarding'). Words are scored, not AND-ed, so extra words only re-order the result.
scopeNoall (default) = personal space plus every workspace; personal = only their own space; workspace = only the workspace this connection is bound to.
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
projectNoWorkspace to run this call in (id or name).
completedNofalse (default) = only OPEN items, what 'still to do' means. true = only finished ones.
due_beforeNoOptional agenda cutoff, only items due at or before it: a day (2026-11-06, through its end) or a date-time with its UTC offset.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / due_before / description
      Previous value: -"Optional agenda cutoff, unix seconds: only items due at or before this."New value: +"Optional agenda cutoff, only items due at or before it: a day (2026-11-06, through its end) or a date-time with its UTC offset."
    • addedInput schema / properties / due_before / pattern
      Added value: +"^\\d{4}-\\d{2}-\\d{2}(T\\d{2}:\\d{2}(:\\d{2}(\\.\\d{1,9})?)?(Z|[+-]\\d{2}:?\\d{2})?)?$"
    • changedInput schema / properties / due_before / type
      Previous value: -"integer"New value: +"string"
  2. Changed1 schema field changed
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / required
      Added value: +[]
  5. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description adds real behavioral context beyond that — cross-workspace aggregation, workspace-first ordering, and open-items-by-default. It stops short of describing pagination/limit behavior or result shape beyond the field list, so it is 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 triggering condition and dense throughout; every clause carries routing or scoping information. Slightly run-on and the synonym enumeration is long, but it is functional vocabulary for intent matching rather than filler.

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 8 all-optional parameters, full schema coverage, and no output schema, the description supplies what is missing: what the results contain (due date, labels, workspace), the default filter (open only), and the ordering. An agent can call this correctly and interpret the result without further information.

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 100%, so baseline is 3; the description earns the bump by clarifying semantics the schema does not state on its own — cross-workspace scope with the bound workspace first, and that the default result set is open items with due date, labels and workspace attached. It does not explain query scoring or the person/project impersonation semantics, which remain schema-only.

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?

States a specific verb (list/return) and resource (the member's Connections to-dos), plus concrete scope: personal space plus every workspace, workspace-first. It explicitly distinguishes itself from the nearest confusable sibling, post_agent_todos_list (the agent work log), and implicitly from connections_todo_add/done/update by being the read path.

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?

Enumerates the user phrasings that should trigger it (to-do list, tasks, open items, reminders, follow-ups, due/overdue, anything waiting on them) and gives an explicit negative case (not the assistant's own work log — that is the agent lane, post_agent_todos_list). It also mandates sourcing answers from this list rather than chat history, which is a genuine usage rule rather than restatement.

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

All Connections 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