FlightPlan

complete_intent

Close out a finished or abandoned intent with a required outcome summary and git facts, so other agents get accurate collision warnings and context on what changed and why.

Instructions

Close out an intent when work finishes or is abandoned. The outcome summary is required for done and is the most valuable artifact this system produces: write one paragraph covering what actually changed, anything surprising, approaches tried and rejected, and anything deliberately left in place. Gather git facts you already have at completion time: files = repo-relative paths actually changed (git diff --name-only over the work, committed or not); commits = SHAs created for this work; uncommitted = true if ANY of the work is not yet committed (untracked/unstaged/staged-only), false if all of it is. True makes other agents' collision checks warn loudly. Outside git, omit uncommitted and commits (there is no commit to wait for), but still send files. Send files: [] only when this work changed no files, committed or not; omit files when you do not know. Omit anything unknown. Any overlaps that come back carry excerpts, and overlaps_omitted counts the ones the server cut per level — use get_intent(id) for a full record.

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": {
      "id": "<id>",
      "status": "<status>",
      "outcome": "<outcome>"
    },
    "name": "complete_intent"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The intent id returned by post_intent.
`files`	No	Repo-relative paths actually changed (from `git diff --name-only` over the work). Send [] only when this work changed no files, committed or not. Omit if unknown.
`status`	Yes	done = landed; abandoned = stopped without landing.
`commits`	No	Commit SHAs produced for this work. Omit if unknown.
`outcome`	Yes	One paragraph: what actually changed, surprises, dead ends, things deliberately left alone.
`uncommitted`	No	True if ANY of the work is not yet committed (untracked/unstaged/staged-only). This flag escalates collision warnings for other agents. False = all committed. Outside git, omit it: there is no commit to wait for. Omit if unknown.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.17.2Oct 28, 2026

changedInput schema / properties / files / description

Previous value: -"Repo-relative paths actually changed (from `git diff --name-only` over the work). Omit if unknown."New value: +"Repo-relative paths actually changed (from `git diff --name-only` over the work). Send [] only when this work changed no files, committed or not. Omit if unknown."

changedInput schema / properties / uncommitted / description

Previous value: -"True if ANY of the work is not yet committed (untracked/unstaged/staged-only). This flag escalates collision warnings for other agents. False = all committed. Omit if unknown."New value: +"True if ANY of the work is not yet committed (untracked/unstaged/staged-only). This flag escalates collision warnings for other agents. False = all committed. Outside git, omit it: there is no commit to wait for. Omit if unknown."

First observedv0.1.0Aug 18, 2026

TDQS

A4/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden, and it does real work: it discloses the downstream effect of `uncommitted=true` (escalated collision warnings for other agents) and describes the response shape (overlaps with excerpts, `overlaps_omitted` counts, pointer to `get_intent`). Minor gap: it says the outcome is 'required for `done`' while the schema requires it for all statuses, a small inconsistency.

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 purpose, then proceeds parameter by parameter with no wasted preamble. It is dense and somewhat long, repeating guidance that already lives in the schema descriptions, but each sentence carries operational instruction rather than filler.

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 6-parameter mutation tool with no annotations and no output schema, the description covers intent, per-parameter semantics, and the key return fields (overlaps excerpts, truncation count, escape hatch to `get_intent`). It stops short of describing error behavior or what happens if the intent was already closed, which would complete the picture.

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 baseline is 3, but the description adds operative meaning: exactly how to derive `files` (repo-relative `git diff --name-only` over the work, committed or not), the strict distinction between sending `[]` and omitting, and why `commits`/`uncommitted` should be omitted outside git. Much of this is mirrored in the schema text, so it is additive rather than transformative.

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 and resource with clear scope: closing out an intent with a terminal status of done or abandoned. It does not, however, distinguish itself from the sibling `mark_intent_landed`, which sounds like it overlaps in the 'landing' case, leaving the agent to infer the difference.

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 a clear trigger condition ('when work finishes or is abandoned') plus detailed guidance on what to include per context (git vs non-git, omit vs empty list). It does not name an alternative tool or state when a different sibling should be used instead.

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

Deploy Server