Skip to main content
Glama
Sign In
MemAI

MemAI

by Filipe-Soares-de-Almeida
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

task_item

Destructive

Update a task item's text, state, comment, or linked memories, or delete it, to keep MemAI task records accurate across sessions.

Instructions

Update one item of a task -- its text, its state, a comment on it, memories linked to it -- or delete it.

Give at least one of text, state, comment and related, or delete. They apply together, or not at all.

The result names the item's number n and the task's title.

Free text cites another item only as [[#id]], which reads back as its current number and label; a label -- a title, an item's text -- never carries one. To a person, name it item n of its task.

Input Schema

NameRequiredDescriptionDefault
uidYesthe task.
itemYesthe item's id, as task_read(part='items') lists it.
textNothe item's new text, a short label as task() takes it. The item keeps its id, state, brief, comments and links; the previous text stays in the edit history.
stateNotodo, doing, done or dropped. The write that closes the last open item archives the task (`archived` in the result); one that reopens an item reopens the task.
deleteNoremoves the item with its comments, links and note attachments, alone in its call. No other item moves; a DEPENDS ON that named it keeps its text, marked deleted, and a brief on only that item stays, on the whole task. Delete a mistake or a duplicate; mark work decided against as dropped, which keeps it.
commentNoa remark on this item -- what blocked it, what was decided.
relatedNocomma-separated uids of memories this item produced or depends on. An unknown uid refuses the whole call, and nothing is written.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv0.16.1
    • addedInput schema / properties / comment / description
      Added value: +"a remark on this item -- what blocked it, what was decided."
    • removedInput schema / properties / comment / title
      Removed value: -"Comment"
    • addedInput schema / properties / delete
      Added value: +{
+  "default": false,
+  "description": "removes the item with its comments, links and note attachments, alone in its call. No other item moves; a DEPENDS ON that named it keeps its text, marked deleted, and a brief on only that item stays, on the whole task. Delete a mistake or a duplicate; mark work decided against as dropped, which keeps it.",
+  "type": "boolean"
+}
    • addedInput schema / properties / item / description
      Added value: +"the item's id, as task_read(part='items') lists it."
    • removedInput schema / properties / item / title
      Removed value: -"Item"
    • changedInput schema / properties / item / type
      Previous value: -"string"New value: +"integer"
    • addedInput schema / properties / related / description
      Added value: +"comma-separated uids of memories this item produced or depends on. An unknown uid refuses the whole call, and nothing is written."
    • removedInput schema / properties / related / title
      Removed value: -"Related"
    • addedInput schema / properties / state / description
      Added value: +"todo, doing, done or dropped. The write that closes the last open item archives the task (`archived` in the result); one that reopens an item reopens the task."
    • removedInput schema / properties / state / title
      Removed value: -"State"
    • addedInput schema / properties / text
      Added value: +{
+  "default": "",
+  "description": "the item's new text, a short label as task() takes it. The item keeps its id, state, brief, comments and links; the previous text stays in the edit history.",
+  "type": "string"
+}
    • addedInput schema / properties / uid / description
      Added value: +"the task."
    • removedInput schema / properties / uid / title
      Removed value: -"Uid"
    • removedInput schema / title
      Removed value: -"task_itemArguments"
  2. Addedv0.6.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds substantial extra behavior: closing the last open item archives the task and reopening reopens it; delete removes comments, links and note attachments and leaves DEPENDS ON referrers marked deleted; an unknown uid refuses the whole call with nothing written. This atomicity and side-effect disclosure goes well beyond the structured hints.

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 verb and resource, then the calling contract, then the return shape and referencing rule. The prose is idiosyncratic ('a label -- a title, an item's text -- never carries one') and slightly verbose in places, but every paragraph carries distinct information.

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 7-parameter mutation tool with no output schema, the description covers the key gaps: which parameters coexist, delete side effects, task archiving/reopening, atomic failure on unknown uid, and the return contents ('the item's number n and the task's title'). Little an agent needs is missing, though delete-only exclusivity could be stated more sharply.

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, but the description adds meaning beyond the schema for the free-text fields: cross-item references must be written as [[#id]] and read back as a number and label, which no schema entry states. It also reinforces the 'all-or-nothing' coupling of the optional parameters.

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 a specific verb pair (update/delete) and a precisely-scoped resource (one item of a task), enumerating the touchable fields (text, state, comment, related memories). An agent can place it apart from task_comment, task_note and task_add by the 'one item' scope, though it never names those siblings as alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explains the calling contract ('Give at least one of text, state, comment and related, or delete. They apply together, or not at all'), which is real operational guidance. However it offers no explicit when-to-use-this-vs-alternatives routing against siblings like task_comment or task_note, which overlap with the 'comment' field.

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

Deploy Server

Other Tools