Skip to main content
Glama

desk_answer

Records a person's answer to a desk item, verifying their exact words against recorded sessions before saving. Supports choices, standing grants, and assumption-batch progress.

Instructions

Record the person's answer to a desk item (D3). words is their reply exactly as they typed it, never your summary: Tares looks for it in the recorded sessions of the person the item is for (any station, any session of theirs). If it is not there yet, you get a retryable error: recordings can take a minute to arrive, so try again after the next sync. Nothing is recorded until the words are found. A reply of one letter ("B") is passed as is: Tares maps it to that option. choice the option it picks, as the option's full text (or, when they chose none, their own answer in a short sentence): on an item with options every decision records one, and free words that name no option are refused (TR-1018). standing only when they said it holds from now on ("always fine for staging"); with scope all it holds for every project. A standing answer that matches becomes a grant given by that person: grant_kind project (the default; with scope all, a team grant, which needs an admin) or personal (for their own machine). A project grant that reaches into repos other people own waits for their consent (grant says what it waits for). For an assumption batch: kept the assumptions they keep, overturned {A3: their words}; open a follow-up ticket for each overturned one.

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": {
      "item": "<item>",
      "words": "<words>"
    },
    "name": "desk_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemYes
keptNo
scopeNoproject
wordsYes
choiceNo
standingNo
grant_kindNoproject
overturnedNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A3.7/5.0
Behavior4/5

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 well: it discloses the retryable-error semantics, that nothing is recorded until the words are found, the TR-1018 refusal for free words naming no option, and the side effects (creating a grant attributed to the person, admin requirement for team grants, consent waits for cross-owner repos, follow-up tickets per overturned assumption). It does not address idempotency or whether repeated calls duplicate records, which keeps it from a 5.

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?

The core action is front-loaded correctly, but the body is a dense run-on of stacked clauses and unexplained jargon ("Tares", "D3", "TR-1018") with no paragraph or bullet structure. Nearly every sentence carries information, yet readability suffers from cramming eight parameters' semantics into one block.

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 an 8-parameter mutation tool with zero schema descriptions, the definition covers most of what an agent needs: parameter meanings, failure and retry behavior, and downstream side effects. An output schema exists, so return values needn't be explained. Remaining gaps are the undefined `item` parameter and unstated idempotency.

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% with 8 parameters, so the description must compensate and largely does: `words` (verbatim, never summarized), `choice` (full option text or short own-answer), `standing`/`scope`, `grant_kind` (project default, personal, team via scope all), `kept`, and `overturned` are all given meaning beyond the bare schema. The `item` parameter is never defined (id? slug?), and the shape of `overturned` is only sketched, so it falls short of complete.

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 first sentence gives a specific verb and resource: "Record the person's answer to a desk item (D3)." That is unambiguous about what the tool does. It never contrasts itself with near siblings such as decide_assumption, even though it handles assumption batches (`kept`/`overturned`), so an agent must infer the boundary on its own.

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

Usage Guidelines3/5

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

Usage conditions are implied throughout: retry after the next sync when words aren't found yet, supply `standing` only when the person said it holds from now on, and use `scope` for all projects. However, there is no explicit when-to-use versus alternative (e.g., decide_assumption for assumption batches) and no stated exclusions. The guidance is operational rather than routing guidance.

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