Skip to main content
Glama

GTD Brain

by com.gtdbrain
OverviewDiscussionsAdmin

create_card

Use this when the user says where a card belongs or what it is: a next action ('add a next action: email Sam the quote'), a project's next step (pass projectId), a project ('new project: plan the offsite'), something they are waiting on someone for, a Someday/Maybe idea, something to keep for reference that needs no action (the Reference column), or a card for a named custom column. Needs the destination columnId from list_columns; kind 'action' only in Next Actions, 'project' only in Projects, 'card' anywhere else. Do not use for a bare 'add / remind me / note' with no list named — use capture (Inbox, no lookup). Do not use for a card that is already on the board ('put the blog post under my launch project', 'make the passport card a next action') — find it with search_cards and move_card or update_card it; a new card plus archive_card on the old one loses its history. Returns the created card.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
whoNoOptional, for Waiting For: who it is delegated to, e.g. 'Sam'.
kindNo'action' for Next Actions, 'project' for Projects, 'card' for every other column. Defaults to 'card'.
notesNoOptional details the user gave.
sinceNoOptional, for Waiting For: since when, e.g. '2026-09-01' or 'last Monday'.
titleYesThe card title: a verb-first next action ('Email Sam the quote'), a project outcome ('Offsite planned'), or the note itself.
contextNoOptional, for actions: the context id, e.g. 'calls'. GTD context id (e.g. calls, computer, errands, home). The user manages their own set — list_contexts shows it, create_context adds one; if unknown, the error lists the valid ids so you can retry.
columnIdYesDestination column id, from list_columns.
projectIdNoOptional, for actions: the project card id (from list_projects) this action moves forward.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / projectId
      Added value: +{
+  "description": "Optional, for actions: the project card id (from list_projects) this action moves forward.",
+  "type": "string"
+}
  2. Changed7 schema fields changed
    • changedInput schema / properties / columnId / description
      Previous value: -"The destination column id (from list_columns)."New value: +"Destination column id, from list_columns."
    • changedInput schema / properties / context / description
      Previous value: -"Optional, for action cards. GTD context id (e.g. calls, computer, errands, home). The user manages their own set — list_contexts shows it, create_context adds one; if unknown, the error lists the valid ids so you can retry."New value: +"Optional, for actions: the context id, e.g. 'calls'. GTD context id (e.g. calls, computer, errands, home). The user manages their own set — list_contexts shows it, create_context adds one; if unknown, the error lists the valid ids so you can retry."
    • changedInput schema / properties / kind / description
      Previous value: -"Card kind. Defaults to 'card'."New value: +"'action' for Next Actions, 'project' for Projects, 'card' for every other column. Defaults to 'card'."
    • changedInput schema / properties / notes / description
      Previous value: -"Optional longer description / body."New value: +"Optional details the user gave."
    • changedInput schema / properties / since / description
      Previous value: -"Optional: since when it's been waiting (Waiting For)."New value: +"Optional, for Waiting For: since when, e.g. '2026-09-01' or 'last Monday'."
    • changedInput schema / properties / title / description
      Previous value: -"The card title (the task or note)."New value: +"The card title: a verb-first next action ('Email Sam the quote'), a project outcome ('Offsite planned'), or the note itself."
    • changedInput schema / properties / who / description
      Previous value: -"Optional: who it's delegated to (Waiting For)."New value: +"Optional, for Waiting For: who it is delegated to, e.g. 'Sam'."
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write, so the safety profile is covered. The description adds real behavioral context beyond that: columnId must be resolved via list_columns first, the kind value is constrained by destination column, and it states what is returned. It does not discuss failure modes or duplicate creation, keeping it short of 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 with actionable content — nearly every clause rules an intent in or out. The middle section is one long run-on chain of cases, which is heavier than ideal but each clause carries routing value, so it is not padding.

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?

For an 8-parameter write tool with no output schema, the description covers prerequisites (columnId from list_columns, projectId from list_projects), value constraints, alternatives, and the return ('the created card'). It omits board position/ordering behavior, which is a minor gap rather than a blocking one.

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 the baseline is 3. The description goes beyond the schema by stating the cross-parameter rule the schema only implies per-field: 'kind action only in Next Actions, project only in Projects, card anywhere else', plus the projectId/lookup requirement. This is genuine added meaning, though per-field examples largely duplicate the schema.

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 and resource (create a card) and then enumerates exactly which user intents map to it — next action, project step, project, waiting-for, Someday/Maybe, reference, custom column. It explicitly distinguishes itself from siblings by naming capture, search_cards, move_card, update_card and archive_card as the wrong tools in specific cases.

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?

Provides explicit when-to-use triggers ('use this when the user says where a card belongs or what it is') and two explicit when-NOT-to-use rules with named alternatives: bare 'add/remind me/note' with no list → capture; a card already on the board → search_cards + move_card/update_card, with a stated reason (archive_card loses history).

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

All GTD Brain toolsInspect
Try in Browser
Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources