Skip to main content
Glama

finish_project

Mark a project done after confirming with the person on the desk and recording their answer, removing it from the crew's work list while blocking closure if any ticket stays open.

Instructions

Mark a project done, once the person said so. Ask them first on the desk ("Is done? Tickets all merged, milestones checked."), record their answer with desk_answer, then call this with that item (decision, D). Tares keeps their words, sets the project done and takes it off the crew's work list; a later hand-over opens it again. Refused while a ticket is open. Only the orchestrator may. Returns how many projects the crew still holds: with none left, ask the person on the desk whether to stop the crew (tares factory crew down in their terminal).

A person's own session (tares factory session, not a crew station) passes words instead: what the person typed when they said it is done, copied exactly. That also finishes a project the crew never held.

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": {
      "project": "<project>"
    },
    "name": "finish_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
wordsNo
projectYes
decisionNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses side effects (project set done, removed from the crew's work list, reopened by a later hand-over), an authorization rule (orchestrator only), a refusal condition, and the return value (count of projects the crew still holds) plus the follow-up action when that count is zero.

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 core action and precondition are front-loaded, and nearly every sentence adds operational information. It is dense rather than bloated, though the embedded quoted desk prompt and the trailing parenthetical about `tares factory crew down` make the later sentences long and slightly winding.

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?

Despite an output schema existing, the description still explains the return count and the next step when it reaches zero, and it covers the no-annotations gap by documenting side effects, permissions, and refusals. Nothing an agent needs to invoke this correctly 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 0%, so the description must compensate, and it does for all three: `decision` is the desk_answer item in D<n> form, `words` is the person's verbatim text for a personal session, and `project` is the target. It stops short of defining the exact `project` identifier format, so it is strong but not exhaustive.

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?

"Mark a project done" gives a specific verb plus resource, and the description immediately scopes it with the authority constraint ("Only the orchestrator may") and the reopening behavior tied to a later hand-over, which separates it from hand_project_to_crew and the other project siblings.

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

Usage Guidelines5/5

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

It spells out the exact preconditions (ask the person on the desk, record the answer with desk_answer, then pass that item as `decision`), states a hard exclusion ("Refused while a ticket is open"), and describes an alternate invocation path for a personal session using `words`. This is explicit when/when-not/alternative guidance.

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