Skip to main content
Glama

add_summary

File a case handover note capturing what was done, what remains, blockers, and the next step, so anyone continuing the task knows exactly where things stand.

Instructions

Files a summary: the handover note of a case, in four parts, none of them empty (entry_fields_invalid lists the empty ones).

A significant step is a decision made, a finished part of the work, a failure that changes the plan, or any point where a colleague would need an explanation of where the work stands.

Its index title is the first line of done, returned in the response. The final summary, with unmeasured, is filed by close_task.

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`
doneYesWhat was done since the previous summary, with references to artifacts. Its first line becomes the entry title in the case index: one sentence about what happened; a longer line is cut at a word boundary
blockersYesWhat stands in the way, or `nothing`. In a summary before `waiting` it names what is awaited and from whom
next_stepYesThe one concrete action a successor starts with. In a summary before `waiting` it is the action taken once the awaited arrives. A doubt about a decision or a result is recorded here, as what to look at and why, rather than as a verdict
remainingYesWhat remains before the task is done
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. Changed20 schema fields changedv0.5.2
    • changedInput schema / properties / blockers / description
      Previous value: -"Что мешает. Пустым это поле быть не может: «ничего», если ничего"New value: +"What stands in the way, or `nothing`. In a summary before `waiting` it names what is awaited and from whom"
    • removedInput schema / properties / blockers / examples
      Removed value: -[
      -  "Ничего"
      -]
    • changedInput schema / properties / done / description
      Previous value: -"Что сделано с прошлой сводки, со ссылками на артефакты. Первая строка становится заголовком записи в описи — одной фразой о случившемся; слишком длинную трекер обрежет по границе слова"New value: +"What was done since the previous summary, with references to artifacts. Its first line becomes the entry title in the case index: one sentence about what happened; a longer line is cut at a word boundary"
    • removedInput schema / properties / done / examples
      Removed value: -[
      -  "Разобрался, где сгорает номер задачи"
      -]
    • 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 / next_step / description
      Previous value: -"Одно конкретное действие, с которого начнёт преемник"New value: +"The one concrete action a successor starts with. In a summary before `waiting` it is the action taken once the awaited arrives. A doubt about a decision or a result is recorded here, as what to look at and why, rather than as a verdict"
    • removedInput schema / properties / next_step / examples
      Removed value: -[
      -  "Перенести вызов next_task_number в конец create_task"
      -]
    • changedInput schema / properties / remaining / description
      Previous value: -"Что осталось до выхода задачи"New value: +"What remains before the task is done"
    • removedInput schema / properties / remaining / examples
      Removed value: -[
      -  "Перенести выдачу номера после валидации"
      -]
    • 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"
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

With annotations providing no positive behavioral hints, the description carries the burden, and it discloses meaningful behavior: empty parts are rejected with entry_fields_invalid, the index title comes from the first line of done, and final summaries are handled elsewhere. This goes beyond the schema's required-field checks.

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?

The description is compact and front-loads the core purpose before adding behavioral and contextual details. The second paragraph on 'significant step' earns its place even if slightly abstract.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a tool with a rich 100%-covered schema and an output schema: it covers purpose, validation behavior, title derivation, content guidance, and the boundary with close_task. Nothing essential is missing.

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 description coverage is 100%, so the baseline is 3. The description adds value by clarifying the four-part structure, requiring none of them to be empty, and explaining that the first line of done becomes the entry title.

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 states a specific verb ('Files') and a specific resource ('a summary: the handover note of a case'), and further distinguishes it by defining the four non-empty parts. This clearly separates add_summary from sibling tools like add_entry and close_task.

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?

The description gives clear context on what constitutes a significant step and explicitly notes that the final summary is filed by close_task, an exclusion that prevents misuse. It does not explicitly name alternatives like add_entry, so it stops short of a 5.

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