Skip to main content
Glama

add_entry

Files immutable case entries—decisions, attempts, findings, artifacts, remarks, or notes—to a task. Correct mistakes by filing a new entry that references the original.

Instructions

Files an entry without payload: a decision, attempt, finding, artifact, remark or note.

Entries are immutable: no call edits or deletes one, and a mistaken entry is corrected by a new entry that references it in refs. Summaries, questions, answers, verdicts and resolutions have their own tools: add_summary, ask, answer, add_verdict, resolve.

An empty title is refused with entry_fields_invalid, which lists the fields.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesTask key `PROJECT-N`, case-insensitive; a previous key of a moved task addresses it as well. An unknown key is refused with `task_not_found`
bodyNoEntry body in markdown, stored and returned as is. It holds what a successor needs to continue; file contents and long outputs stay outside it, represented by a pointer and the gist
refsNoReferences: task entries `TRK-42#12`, project entries `TRK#7`, tasks `TRK-7`, or a URL with a scheme (`https://…`, `file://…`). Anything else (`7`, `#7`, `docs/x.md`) is refused with `entry_fields_invalid`, as is an entry, task or project that does not exist; URLs are not checked
typeYesWhat the entry records: - `decision` — an option chosen among several, with the reason; - `attempt` — something tried and how it ended, failed attempts included; - `finding` — an established fact with its source, including what was learned from reading; - `artifact` — a pointer to a result; - `remark` — a claim that finished work of a task came out wrong, written from the side of whoever needs the result; the task's assignee resolves it with `resolve`. A remark on a closed task is accepted: the case grows, the task stays as it is. An observation about the caller's own task is a `finding`, not a `remark`; - `note` — an entry that fits none of the types above
titleYesEntry title: its line in the case index of `get_task`. It states what happened, not how
idempotency_keyNoRetry key chosen by the caller, e.g. a UUID. A repeat with the same key and the same arguments returns the first result and creates nothing; the same key with other arguments is refused with `idempotency_key_reused`. A key is bound to the caller's token and kept for 24 hours

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noYesEntry number in the task's case; with the key it forms `TRK-42#12`
seqYesJournal sequence number, usable as `after` of `wait_journal`
titleYesThe title the tracker built, for entry types whose title is not sent (summary, answer, verdict, resolution, service entries); `null` when the caller sent the title
authorYes
task_keyYes
created_atYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.1
    • changedInput schema / properties / refs / description
      Previous value: -"References: task entries `TRK-42#12`, project entries `TRK#7`, tasks `TRK-7`, URLs. An entry, task or project that does not exist is refused with `entry_fields_invalid`; URLs are not checked"New value: +"References: task entries `TRK-42#12`, project entries `TRK#7`, tasks `TRK-7`, or a URL with a scheme (`https://…`, `file://…`). Anything else (`7`, `#7`, `docs/x.md`) is refused with `entry_fields_invalid`, as is an entry, task or project that does not exist; URLs are not checked"
  2. Changed19 schema fields changedv0.5.2
    • changedInput schema / properties / body / description
      Previous value: -"Тело записи в markdown; хранится и отдаётся как есть"New value: +"Entry body in markdown, stored and returned as is. It holds what a successor needs to continue; file contents and long outputs stay outside it, represented by a pointer and the gist"
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Ключ повтора, который ты придумываешь сам (обычно UUID). Повтор вызова с тем же ключом и теми же аргументами отвечает первым результатом и второго объекта не заводит; тот же ключ с другими аргументами отклоняется. Ключ живёт в паре с твоим токеном и помнится 24 часа"New value: +"Retry key chosen by the caller, e.g. a UUID. A repeat with the same key and the same arguments returns the first result and creates nothing; the same key with other arguments is refused with `idempotency_key_reused`. A key is bound to the caller's token and kept for 24 hours"
    • changedInput schema / properties / key / description
      Previous value: -"Ключ задачи, например `TRK-42`. Регистр не важен"New value: +"Task key `PROJECT-N`, case-insensitive; a previous key of a moved task addresses it as well. An unknown key is refused with `task_not_found`"
    • changedInput schema / properties / refs / description
      Previous value: -"Ссылки: записи `TRK-42#12`, задачи `TRK-7`, адреса. Записи и задачи проверяются на существование, адреса — нет"New value: +"References: task entries `TRK-42#12`, project entries `TRK#7`, tasks `TRK-7`, URLs. An entry, task or project that does not exist is refused with `entry_fields_invalid`; URLs are not checked"
    • changedInput schema / properties / refs / examples
      Previous value: -[
      -  [
      -    "TRK-42#3"
      -  ]
      -]New value: +[
      +  [
      +    "TRK-42#12"
      +  ]
      +]
    • changedInput schema / properties / title / description
      Previous value: -"Заголовок записи: он стоит в описи дела, которую отдаёт `get_task`"New value: +"Entry title: its line in the case index of `get_task`. It states what happened, not how"
    • removedInput schema / properties / title / examples
      Removed value: -[
      -  "Выбран asyncpg вместо psycopg: нужен LISTEN без потока"
      -]
    • changedInput schema / properties / type / description
      Previous value: -"Что случилось: `decision` — выбран вариант из нескольких, `attempt` — попытка и чем кончилась (провал ценнее успеха), `finding` — установленный факт с источником, `artifact` — указатель на результат, `remark` — замечание «вышло не то» к чужой сделанной работе, `note` — всё остальное, и это последний выбор. Сводка, вопрос, ответ, вердикт и резолюция подшиваются своими инструментами"New value: +"What the entry records:\n- `decision` — an option chosen among several, with the reason;\n- `attempt` — something tried and how it ended, failed attempts included;\n- `finding` — an established fact with its source, including what was learned from reading;\n- `artifact` — a pointer to a result;\n- `remark` — a claim that finished work of a task came out wrong, written from the side of whoever needs the result; the task's assignee resolves it with `resolve`. A remark on a closed task is accepted: the case grows, the task stays as it is. An observation about the caller's own task is a `finding`, not a `remark`;\n- `note` — an entry that fits none of the types above"
    • removedInput schema / properties / type / examples
      Removed value: -[
      -  "decision"
      -]
    • removedOutput schema / $defs / AuthorKind
      Removed value: -{
      -  "description": "Кто именно сделал действие.\n\n`tracker` — сам трекер: этим родом подписаны служебные записи дела и строки,\nзаведённые командой первичной инициализации. У него нет подписи, потому что\nназывать себя по имени ему незачем: трекер в установке один.",
      -  "enum": [
      -    "agent",
      -    "human",
      -    "tracker"
      -  ],
      -  "title": "AuthorKind",
      -  "type": "string"
      -}
    • changedOutput schema / $defs / AuthorView / description
      Previous value: -"Кто сделал действие: род и подпись. У самого трекера подписи нет."New value: +"Who acted: kind and signature. The tracker itself has no signature."
    • removedOutput schema / $defs / AuthorView / properties / kind / $ref
      Removed value: -"#/$defs/AuthorKind"
    • addedOutput schema / $defs / AuthorView / properties / kind / description
      Added value: +"Kind of author. `tracker` signs the service entries the tracker files itself"
    • addedOutput schema / $defs / AuthorView / properties / kind / enum
      Added value: +[
      +  "agent",
      +  "human",
      +  "tracker"
      +]
    • addedOutput schema / $defs / AuthorView / properties / kind / type
      Added value: +"string"
    • changedOutput schema / description
      Previous value: -"Ответ подшивающего инструмента: чем запись адресуют, без самой записи.\n\n`title` непуст только там, где заголовок собрал трекер: у сводки, ответа, вердикта и\nрезолюции его не принимают вовсе (`app/domain/case.py`, `TITLED_ENTRY_TYPES`). Где\nзаголовок прислал агент, здесь стоит `null` — «в описи ровно то, что ты прислал»."New value: +"A filed entry, by its address rather than its content; the entry in full is\nreturned by `read_entries`."
    • addedOutput schema / properties / no / description
      Added value: +"Entry number in the task's case; with the key it forms `TRK-42#12`"
    • addedOutput schema / properties / seq / description
      Added value: +"Journal sequence number, usable as `after` of `wait_journal`"
    • addedOutput schema / properties / title / description
      Added value: +"The title the tracker built, for entry types whose title is not sent (summary, answer, verdict, resolution, service entries); `null` when the caller sent the title"
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false), it discloses the crucial immutability trait: no call edits or deletes an entry, and corrections happen via a new entry referencing the old one in `refs`. It also surfaces failure modes (`entry_fields_invalid`). It does not flag the idempotency_key behavior that the annotation leaves implicit, but the compatibility with destructiveHint=false is consistent.

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

Conciseness5/5

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

Three short, front-loaded paragraphs: purpose first, immutability and correction second, sibling routing third. No filler and the most decision-relevant facts come first.

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?

With a rich schema and an output schema available, the description supplies exactly the runtime facts the structured fields cannot: immutability, correction-by-reference, and the sibling-tool boundaries. The one slightly cryptic phrase is 'without payload', which could confuse an agent about whether `body` is expected.

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 nonetheless adds meaning by explaining that `refs` is the correction mechanism for immutable entries and that an empty title is refused. This goes beyond restating parameter names, though the per-parameter detail still lives mostly in 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?

The description opens with a specific verb+resource ('Files an entry') and enumerates the exact entry types it accepts. It explicitly separates itself from siblings by naming the categories that have their own tools (summaries, questions, answers, verdicts, resolutions).

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?

It names the alternative tools (`add_summary`, `ask`, `answer`, `add_verdict`, `resolve`) and reserves `add_entry` for the remaining kinds of records. It does not, however, explicitly route the caller away from `add_project_entry` or clarify project-vs-task entry choice, so the guidance is clear but not fully closed.

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