Skip to main content
Glama

misakanet_submit_intake

Submit a failure-case intake when no lesson matches, a lesson is stale or incorrect, or a user resolves an undocumented problem, so MisakaNet can review and file it as an issue.

Instructions

Submit a failure-case intake when no matching lesson exists or a lesson was stale/incorrect. Use after misakanet_search fails to find a good match, or when the user resolved a problem not yet documented. Input semantics: problem is required (short description of the failure); kind defaults to missing_lesson; error, what_tried, fix, verification, and matched_lesson_id are optional. Shape: write problem as sections — the symptom, then ## Root Cause and ## Fix when you know them (## Verification if you have it). Without a root cause the report is still filed, but it cannot become a lesson automatically — it waits for a person. Output schema: JSON with submitted (boolean), intake_id, status (pending_review), redactions_applied, quality_score, dedup_key, poll_hint, and receipt. Error cases: missing problem, duplicate submission. Side effects: files the report on MisakaNet (it becomes a GitHub issue); when the network is unreachable it is kept in the local queue only, and the receipt says so via delivery=local_queue. Auth: none. Rate limits: the hosted endpoint's.

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": {
      "problem": "<problem>"
    },
    "name": "misakanet_submit_intake"
  }
}

Input Schema

NameRequiredDescriptionDefault
fixNoOptional: how the problem was resolved, if known.
kindNoType of intake. missing_lesson = no match found; stale_lesson = matched but wrong; new_lesson_candidate = user resolved a new problem; question = asking for help (opens a [Question] issue, not a lesson candidate); proposal = a plan or product request, explicitly not a failure report (answerable by a decision, never converted into a lesson).
errorNoOptional short error message.
sourceNoCalling client: codex, claude-code, cursor, dsh, curl, or other.
problemYesRequired. The symptom first, then a `## Root Cause` section and a `## Fix` section when known (max 2000 chars). Reports with those sections can become lessons automatically.
what_triedNoOptional: what was attempted before or during the failure.
contributorNoOptional attribution for the filed issue (a GitHub username or an agent name). The hosted surface records it on the issue; omit it and the report stays unattributed.
notify_emailNoOptional, questions only: an email for the ANSWER. Ask the user first; never invent it. One confirmation message is sent now, and one notification (the issue URL, never your text) once the answer is ready. Omit it and the me_inbox / FAQ pull path is unchanged.
verificationNoOptional: how to confirm the fix works.
matched_lesson_idNoOptional: lesson ID that was checked but did not help (for stale_lesson).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.11.3
    • addedInput schema / properties / notify_email
      Added value: +{
      +  "description": "Optional, questions only: an email for the ANSWER. Ask the user first; never invent it. One confirmation message is sent now, and one notification (the issue URL, never your text) once the answer is ready. Omit it and the me_inbox / FAQ pull path is unchanged.",
      +  "type": "string"
      +}
  2. Changed2 schema fields changedv3.5.0
    • addedInput schema / properties / contributor
      Added value: +{
      +  "description": "Optional attribution for the filed issue (a GitHub username or an agent name). The hosted surface records it on the issue; omit it and the report stays unattributed.",
      +  "type": "string"
      +}
    • changedInput schema / properties / problem / description
      Previous value: -"Required short description of the failure or gap (max 2000 chars)."New value: +"Required. The symptom first, then a `## Root Cause` section and a `## Fix` section when known (max 2000 chars). Reports with those sections can become lessons automatically."
  3. Changed2 schema fields changedv3.3.0
    • changedInput schema / properties / kind / description
      Previous value: -"Type of intake. missing_lesson = no match found; stale_lesson = matched but wrong; new_lesson_candidate = user resolved a new problem."New value: +"Type of intake. missing_lesson = no match found; stale_lesson = matched but wrong; new_lesson_candidate = user resolved a new problem; question = asking for help (opens a [Question] issue, not a lesson candidate); proposal = a plan or product request, explicitly not a failure report (answerable by a decision, never converted into a lesson)."
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "missing_lesson",
      -  "stale_lesson",
      -  "new_lesson_candidate"
      -]New value: +[
      +  "missing_lesson",
      +  "stale_lesson",
      +  "new_lesson_candidate",
      +  "question",
      +  "proposal"
      +]
  4. Changed1 schema field changedv2.21.0
    • changedInput schema / properties / error / description
      Previous value: -"Optional short error message (auto-redacted)."New value: +"Optional short error message."
  5. Addedv2.17.1

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the GitHub-issue side effect, the local-queue fallback when the network is unreachable (flagged via delivery=local_queue in the receipt), auth being unneeded, host rate limits, and the two error cases (missing problem, duplicate submission). It also explains a non-obvious consequence — a report without a root cause is filed but cannot auto-become a lesson — which is exactly the kind of behavioral detail annotations cannot express.

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 purpose and when-to-use, then input semantics, output, errors, side effects, auth, rate limits in a predictable order. It is dense and slightly run-on, and the optional-parameter recital duplicates the schema, but almost every clause carries information an agent would otherwise have to guess.

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?

For a 10-parameter write tool with no output schema, the description supplies the missing return-value information (submitted, intake_id, status, dedup_key, receipt, poll_hint) and the failure modes. Nothing material for correct invocation is absent.

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 already 100%, so most of the input-semantics sentence restates the schema. It still adds real meaning by prescribing the `## Root Cause` / `## Fix` / `## Verification` section shape for problem and tying it to automatic lesson conversion, which the schema hints at only briefly.

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 opening sentence names a specific verb and resource ("Submit a failure-case intake") plus the triggering conditions (no matching lesson, or a stale/incorrect lesson). It clearly separates itself from misakanet_search, though it never distinguishes itself from misakanet_write_lesson, which an agent could reasonably confuse with filing an intake.

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?

Usage is explicit: "Use after misakanet_search fails to find a good match, or when the user resolved a problem not yet documented," and the kind enum descriptions map each intake type to a situation. Only the boundary with misakanet_write_lesson is left unstated, so it stops short of full when/when-not guidance.

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