Skip to main content
Glama
Federal Courts Analyst

Federal Courts Analyst

Keep this answer (sandbox)

keep_answer
Idempotent

Validate and save an answer you just gave; optionally file an office inquiry about a changed figure, store a verified copy, or set change notifications.

Instructions

Use this when the user asks to keep an answer you just gave: to ask the statistics office why a figure changed ('ask_office'), to save a verified copy ('verified_copy'), or to be told if its numbers change ('notify'). It checks the answer and, only if it passes, creates the request, saves the answer and (for 'ask_office') files the inquiry. Never call it on your own initiative.

Not for answering questions (use the read tools), for checking if a figure can go to the office (use check_inquiry_eligibility), or for following up (use my_requests).

Returns whether it was saved; if not, each problem with the number and the fix; if so, the request, inquiry and stamp to quote. Pass the answer's citations and the read tools it used (tool_calls). confirm=false writes nothing and returns a preview_id: describe the save, ask 'Shall I go ahead?', and only after a yes call with confirm=true and that preview_id. Changed text, or a retry after a refusal, needs a new preview. Sandbox: nothing reaches the AO or FJC.

Example: option='ask_office', inquiry={measure: 'weighted_civil_filings_per_judgeship', fiscal_year: 2020}, an answer quoting 322 (JFF-2025) and 554 (JB-2020) → saved, inquiry #1.

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": {
      "option": "<option>",
      "question": "<question>",
      "answer_text": "<answer_text>",
      "citations": "<citations>"
    },
    "name": "keep_answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
optionYesWhat the user wants kept.
confirmNoTrue once the user has agreed to this write. False (default) asks the user, or returns a preview if the client can't ask.
inquiryNoFor 'ask_office': the revised figure to ask about.
questionYesThe question.
citationsYesEach official figure the answer quotes, with the edition it was quoted from.
asker_nameNoA display name for the asker (demo identity; the same name must be used for every call about one request).MCP user
asker_roleNoWho is asking.public
preview_idNoWith confirm=true: the preview_id from the confirm=false call the user said yes to.
tool_callsNoThe read tools the answer relied on (name and arguments, e.g. explain_change with its arguments). The server re-runs them; numbers their outputs hold count as backed. Never send values.
answer_textYesThe answer.
idempotency_keyNoAny unique string; a retried call with the same key returns the first result instead of writing again.

Output Schema

NameRequiredDescriptionDefault
dataNo
statusNook
declinedNo
warningsNo
provenanceNo
clarificationNo
suggested_nextNoHints for a follow-up call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Goes well past the annotations: it discloses that the write only happens if the answer passes validation, that ask_office also files an inquiry, that confirm=false writes nothing and returns a preview_id, that changed text or a post-refusal retry invalidates a preview, and that nothing reaches the AO or FJC in sandbox. The annotations already flag a non-read-only, idempotent, non-destructive local write, and the description adds the substantive mechanics around it. Minor gap: it doesn't say what the 'stamp' is beyond something to quote.

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 trigger, then exclusions, then return contract, then the confirm workflow, then an example — a sensible order with no filler. It is dense to the point of being terse in places (the combined create/save/file sentence), but every sentence carries operative information.

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?

An 11-parameter mutation tool with a multi-step confirmation protocol, and the description covers the trigger, the mode semantics, the preview loop, the validation-failure return shape, and a concrete worked example. An output schema exists, so return values need not be detailed, yet the description still tells the agent what to surface on success and failure.

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 the baseline is 3, and the description earns above that by explaining the otherwise non-obvious protocol linking confirm=false to preview_id, requiring a fresh preview after text changes, and warning that tool_calls must carry names/arguments, never values. It leaves asker_name, asker_role, and idempotency_key entirely to the schema, which is acceptable given full coverage.

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?

States the specific action ('keep an answer you just gave') and immediately enumerates the three modes (ask_office, verified_copy, notify) with their distinct effects. It explicitly rules out answering questions, eligibility checking, and follow-ups by naming check_inquiry_eligibility and my_requests, so an agent can separate it from siblings without opening any schema.

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?

Explicit trigger ('when the user asks to keep an answer'), explicit prohibition ('Never call it on your own initiative'), and three named alternatives with the condition that selects each. This is a full when/when-not/alternative mapping.

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