Skip to main content
Glama

Say a task is finished

say_done
Idempotent

Mark a task as done when all steps are ticked and parts marked, including evidence in the body. Refused if any step remains unticked or part open.

Instructions

Say a task is done when you did the work, in the turn it ends; on any task, as your word. Refused while a step is unticked or a part open and unmarked. What stopped mattering is say_not_doing. Nothing closes: the person decides. Say it once; news after goes in note.

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>",
      "body": "<body>"
    },
    "name": "say_done"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesWhat you did and what makes you sure (the command and its answer, the commit), in the Tisty language
taskYesThe task id

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.43.2
    • changedInput schema / properties / body / description
      Previous value: -"The account the person reads before deciding: what you did and what makes you sure — the command you ran and what it answered, the commit. In the Tisty language"New value: +"What you did and what makes you sure (the command and its answer, the commit), in the Tisty language"
    • changedInput schema / properties / task / description
      Previous value: -"The task's id, as `find` or `propose` gave it"New value: +"The task id"
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare non-destructive, idempotent, non-read-only, and the description adds behavior an agent could not infer: the call is refused while steps are unticked or parts unmarked, the task is not actually closed by the call, and it should be said once with later updates going to `note`. It stops short of saying what a refusal looks like or whether repeat calls are silently deduplicated.

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

Conciseness3/5

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

It is short and front-loaded, and every clause carries distinct information (trigger, refusal, alternative, non-closure, once-only). But the telegraphic phrasing ('as your word', 'a part open and unmarked') costs parsing effort that a plainly worded sentence would not, so density here is not entirely free.

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 only two required parameters, full schema coverage, and existing annotations, the description covers the remaining gaps an agent needs: preconditions, the fact that nothing is closed, and where follow-up information belongs. An output schema is absent, but the description's 'Nothing closes' preempts the one return-value question that matters.

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% and both parameters are documented in the schema, including what `body` should contain (what you did, the command and its answer, the commit). The description's 'in the turn it ends' adds only a faint timing nuance about `body`, so the baseline 3 applies.

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 establishes a specific speech act on a specific resource ('Say a task is done... for the task id') and immediately clarifies the key ambiguity the title creates: 'Nothing closes: the person decides', so the agent knows this records a claim rather than mutating task state to closed. It also disambiguates from the sibling 'say_not_doing'. The verb 'say' remains slightly obscure about the mechanical effect, which keeps it off a 5.

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 gives an explicit trigger ('when you did the work, in the turn it ends'), a precondition for refusal ('while a step is unticked or a part open and unmarked'), and routes two competing cases elsewhere: abandoned work to `say_not_doing` and follow-up news to `note`. What it lacks is a plain statement of when *not* to use it beyond the unticked-step case.

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