Skip to main content
Glama

Read a whole task

read
Read-onlyIdempotent

Retrieve a task’s full details—steps, document, journal notes, parts, and files—before adding notes or making changes; use fields to narrow the response.

Instructions

Everything a task holds: steps, its document page with the description and your notes, the latest journal notes (ids for reword_note) and who wrote them, parts and files. Read it before noting or mending; fields narrows it. A closed task comes with closed and a notice: it is history, and nothing on it changes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>"
    },
    "name": "read"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesThe task id
notesNoHow many latest journal notes, each cut at 4000 chars; 0: all, whole
fieldsNoOnly these keys of the answer; the id always comes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.47.0
    • changedInput schema / properties / fields / description
      Previous value: -"Only these, the id always: title, status, closed, notice, date, deadline, standing, reminders, tags, source, list, priority, by_agent, via, said_done, said_not_doing, open_to_agents, part_of, parts, description, steps, journal, kept, document"New value: +"Only these keys of the answer; the id always comes"
    • addedInput schema / properties / notes
      Added value: +{
      +  "description": "How many latest journal notes, each cut at 4000 chars; 0: all, whole",
      +  "type": "integer"
      +}
  2. Changed1 schema field changedv1.43.2
    • changedInput schema / properties / fields / description
      Previous value: -"Only these parts of it: any of title, status, closed, notice, date, deadline, standing, reminders, tags, source, list, priority, by_agent, via, said_done, said_not_doing, open_to_agents, part_of, parts, description, steps, journal, kept, document. Left out, everything comes. The id always does"New value: +"Only these, the id always: title, status, closed, notice, date, deadline, standing, reminders, tags, source, list, priority, by_agent, via, said_done, said_not_doing, open_to_agents, part_of, parts, description, steps, journal, kept, document"
  3. Changed1 schema field changedv1.39.1
    • changedInput schema / properties / fields / description
      Previous value: -"Only these parts of it: any of title, status, closed, notice, date, deadline, reminders, tags, source, list, priority, by_agent, via, said_done, said_not_doing, open_to_agents, part_of, parts, description, steps, journal, kept, document. Left out, everything comes. The id always does"New value: +"Only these parts of it: any of title, status, closed, notice, date, deadline, standing, reminders, tags, source, list, priority, by_agent, via, said_done, said_not_doing, open_to_agents, part_of, parts, description, steps, journal, kept, document. Left out, everything comes. The id always does"
  4. First observed

TDQS

A3.9/5.0
Behavior4/5

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

The annotations already declare this a safe, idempotent read, so the description sensibly spends its words elsewhere: what the payload contains, that closed tasks return `closed` plus a `notice` and are immutable, and that notes are trimmed per entry. That is useful context an agent cannot get from the annotations alone.

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?

Two sentences, front-loaded with the returned contents, then the usage rule, then the closed-task caveat — no filler. "it is history, and nothing on it changes" restates the same idea twice, a minor redundancy in an otherwise tight definition.

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 read-only tool with no output schema, the description does the necessary work by sketching the response shape, the role of `fields`, and the special closed-task case. Edge behavior such as an unknown task id or very large tasks is left to the schema or server, but nothing essential is missing.

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 coverage is 100%, so all three parameters are already documented structurally; the description only reinforces that `fields` narrows the answer. The mention of note ids being usable with `reword_note` adds a little practical meaning to `notes`, but no syntax or default behavior is contributed beyond the schema.

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?

The description states a concrete verb (read) and resource (a whole task) and enumerates exactly what the answer contains: steps, the document page with description and notes, latest journal notes with authors, parts and files. That makes the scope of this tool much clearer than the sibling `read_doc` or `describe`, though it never names a sibling explicitly to contrast with.

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?

"Read it before noting or mending" gives an explicit sequencing rule, and the note that a closed task is history with nothing changing on it tells the agent not to attempt edits. It stops short of naming a concrete alternative for reading only the document (e.g. `read_doc`), so no full when/when-not routing is provided.

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