Skip to main content
Glama

Propose a task

propose

Propose a task with steps, parts, tags, dates and reminders so your agent files it into Tisty's local lists. Use it to capture what has to be done and keep it readable later.

Instructions

Propose a task, something to do; what is kept to read again is write_doc. Several from one thread go in tasks, each judged alone. Work of several tasks with one end goes in parts, not packed into steps. An idea named as source leaves Brainstorm. Tisty tags it #agent.

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": "propose"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoThe day it is meant to be done, or with a deadline the day work starts (2026-08-31)
listNoAn existing list, by name, as `catch_up` names it. Left out, it lands in the inbox, which needs a reason
tagsNoIts subjects, one plain word each, reusing the tags `catch_up` shows; six is already a lot
againNoOnly when the person asks in this conversation to redo what was filed from this source and closed since, never for one still open; say in the description how the last one ended
partsNoIts parts, each shaped like a single task with its own steps: one level, at most 32 here, more later with `part_of`
stepsNoA checklist, each step at most 100 characters; what needs more is a part
tasksNoSeveral tasks, each shaped like a single one, at most 32; left out for one
titleNoWhat has to be done, in a line
remindNoWhen to ring, like 2026-08-30T20:00: only for a one-off at a set hour that cannot be caught up on, the evening before
sourceNoWhere you read it: a message id, a thread link
part_ofNoId of an open task this one is a part of
deadlineNoThe day it truly runs out (2026-08-31); only then is it overdue
priorityNoOnly if someone said so
descriptionNoWhat you read, in the Tisty language

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.47.0
    • changedInput schema / properties / list / description
      Previous value: -"An existing list, by name (`lists`). Left out, it lands in the inbox, which needs a reason"New value: +"An existing list, by name, as `catch_up` names it. Left out, it lands in the inbox, which needs a reason"
    • changedInput schema / properties / part_of / description
      Previous value: -"Id of a task you may work on that this one is a part of"New value: +"Id of an open task this one is a part of"
    • changedInput schema / properties / tags / description
      Previous value: -"Its subjects, one plain word each, reusing what `tags` lists; six is already a lot"New value: +"Its subjects, one plain word each, reusing the tags `catch_up` shows; six is already a lot"
    • changedInput schema / properties / tasks / description
      Previous value: -"Several tasks, each shaped like a single one; left out for one"New value: +"Several tasks, each shaped like a single one, at most 32; left out for one"
  2. Changed11 schema fields changedv1.43.2
    • changedInput schema / properties / again / description
      Previous value: -"Only when the person asks you in this conversation to do again what was already proposed from this source and closed since: files a new task despite the source being known. Say in the description how the last one ended. Never for a source whose task is still open"New value: +"Only when the person asks in this conversation to redo what was filed from this source and closed since, never for one still open; say in the description how the last one ended"
    • changedInput schema / properties / date / description
      Previous value: -"The day it is meant to be done, or with a deadline the day the work starts (2026-08-31)"New value: +"The day it is meant to be done, or with a deadline the day work starts (2026-08-31)"
    • changedInput schema / properties / deadline / description
      Previous value: -"The day it actually runs out (2026-08-31): only once it passes is the task overdue"New value: +"The day it truly runs out (2026-08-31); only then is it overdue"
    • changedInput schema / properties / list / description
      Previous value: -"The existing list it belongs in, by name; `lists` says which. Expected: left out, it lands in the inbox, and that needs a reason"New value: +"An existing list, by name (`lists`). Left out, it lands in the inbox, which needs a reason"
    • changedInput schema / properties / part_of / description
      Previous value: -"The id of a task you may work on — one an agent filed, or one the person opened to agents — that this one is a part of"New value: +"Id of a task you may work on that this one is a part of"
    • changedInput schema / properties / parts / description
      Previous value: -"The tasks the work is made of, each shaped like a single one with its own steps; the task around them is finished when they are. One level, at most 32 here — add more later with `part_of`"New value: +"Its parts, each shaped like a single task with its own steps: one level, at most 32 here, more later with `part_of`"
    • changedInput schema / properties / priority / description
      Previous value: -"Only if someone said so. Leave it out otherwise"New value: +"Only if someone said so"
    • changedInput schema / properties / remind / description
      Previous value: -"When to ring, each like 2026-08-30T20:00. Only for what happens once at a set time and cannot be caught up on — an appointment, a flight — set the evening before; never for work any day will do, nor for what repeats"New value: +"When to ring, like 2026-08-30T20:00: only for a one-off at a set hour that cannot be caught up on, the evening before"
    • changedInput schema / properties / source / description
      Previous value: -"Where you read it — a message id, a thread link"New value: +"Where you read it: a message id, a thread link"
    • changedInput schema / properties / tags / description
      Previous value: -"The subjects it is about, one word each in the person's plain words; capitals and accents decide nothing. Six is already a lot, and a word that merely appears in the title is no subject. Reuse what `tags` lists when it means the same"New value: +"Its subjects, one plain word each, reusing what `tags` lists; six is already a lot"
    • changedInput schema / properties / tasks / description
      Previous value: -"Several at once, each shaped like a single one. Left out when proposing one"New value: +"Several tasks, each shaped like a single one; left out for one"
  3. Changed2 schema fields changedv1.39.1
    • changedInput schema / properties / date / description
      Previous value: -"The day it is meant to be done (2026-08-31)"New value: +"The day it is meant to be done, or with a deadline the day the work starts (2026-08-31)"
    • changedInput schema / properties / deadline / description
      Previous value: -"The day it actually runs out (2026-08-31)"New value: +"The day it actually runs out (2026-08-31): only once it passes is the task overdue"
  4. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent local write, so the safety profile is covered. The description adds a useful side effect ("Tisty tags it #agent") and the odd note that an idea with `source` "leaves Brainstorm", but says nothing about what is returned or what happens on failure.

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

Conciseness3/5

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

It is short and front-loads the task-vs-document distinction, but the prose is telegraphic to the point of ambiguity — clauses like "each judged alone" and "An idea named as `source` leaves Brainstorm" cost the reader more than a clear sentence would. Every sentence is load-bearing, yet several are not immediately parseable.

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 a 14-parameter write tool with full schema coverage, no output schema, and annotations covering safety, the description covers the genuinely confusing parts: task vs document, one task vs `tasks`, `parts` vs `steps`. It omits anything about results or verification, but the schema and annotations shoulder most of the rest.

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 earns more by explaining relationships the schema only hints at — that `parts` is for work of several tasks sharing one end and must not be flattened into `steps`, and that `source` moves an idea out of Brainstorm. The `again` redo semantics and tag limits are carried by the schema rather than the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the verb and resource plainly ("Propose a task, something to do") and explicitly contrasts it with `write_doc`, which is for material kept to read again. That distinction lets an agent separate task capture from document storage, though the remaining sentences are too compressed to reinforce the core purpose.

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?

Gives one explicit alternative and the condition that selects it (`write_doc` for reference material), plus batching rules — several tasks in `tasks`, multi-task work in `parts` rather than crammed into `steps`. It never addresses other plausible siblings such as `plan`, `note`, or `remind`, so routing against those is left to inference.

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