Skip to main content
Glama

Report a problem

report_gap

FILE A TICKET on Lucerna itself — the platform's own homework list. Three things put you here: a verb that does not exist (missing), a door that answered and its answer is not true (wrong), or a door that worked and the RESULT was bad — a page that built ugly, an answer that was thin, a refusal that named a way out this caller does not have (poor). The third one matters as much as the other two and is the one agents skip, because nothing stopped you. If your human would not be happy with what this platform just produced, that is a ticket. CHECK IT IS NOT A MODULE YOU DO NOT HAVE. A verb missing from your catalog may be switched OFF for this shop rather than absent from the platform — upgrade.list and modules.off say which, and 'there is no verb for this anywhere' is the one claim this queue cannot verify for you. A ticket asking us to build something that already ships aims the roadmap at work nobody needs. FILE IT LIKE A SPEC, NOT A COMPLAINT. want is the one sentence. expected is the acceptance line — what a correct answer would have looked like, concretely enough that somebody could tell when it is done. answered is WHAT THE DOOR ACTUALLY SAID, quoted short, and it is the single most useful field you can send: the difference between a knob that is missing and a whole mechanism that is missing is usually sitting verbatim in the refusal you just read. Do not characterise it — quote it. YOU GET TWO HANDLES BACK: A TICKET NUMBER (pg_…) AND A RECEIPT (pr_…), ONE RECEIPT PER FILING. Tickets are private to their signed-in reporters: gap_check with the ticket id says where your report got to and shows the text and thread to the reporter who created the ticket, and when we think we have fixed it the ticket goes PENDING carrying the literal test you can run to check us. gap_reply with verdict fixed closes it, still_broken sends it straight back to the queue with your sentence as the reason. The RECEIPT is the handle for ONE FILING, and only its SHA-256 is stored — it cannot be recovered if you lose it. gap_check with a receipt reads back YOUR OWN want, expected and answered as you filed them plus the ticket's state, redacted shipped and verify; never another reporter's words, never the thread, never a verdict. An anonymous filing is still counted toward the same work, and its receipt is how it can be followed: gap_reply with a receipt may add a sentence, but only the signed-in reporter who created the ticket can give the verdict. Report it again while signed in if you need the whole ticket and thread. A second signed-in reporter who files the same wall is counted too, but only the reporter who created the ticket reads its thread or gives the verdict. Nothing here waits on you and no reply is required, but a reporter who checks a fix is the only evidence this platform has that one held. The public roadmap shows only worked tickets with identifiers removed. CAPS AND RETRIES. A signed-in caller may file 50 new tickets in a rolling 24 hours; an anonymous caller gets 10 per egress address, so callers sharing one address share that budget. Over the cap the door refuses and names the exact time to retry. Pass idempotency_key (up to 64 characters) on a call you might repeat: a signed-in caller with the same key gets the SAME receipt and the SAME ticket and nothing is counted twice; an anonymous caller replays only a byte-identical filing, so two people behind one address can never land on each other's filing. An identical report from anybody else collapses onto the same line, so a wall a hundred agents hit reads as a hundred rather than as a hundred tickets, and that count is what decides what gets built next. A later report fills in fields an earlier one left blank, so send what you have even when it is partial. Report what you MEASURED, never what you imagine — this is a homework list, not a wishlist, and one speculative feature request buries the real ones. Do NOT send your human's brief or anything that identifies them: it is their document, no tool here accepts one, and a long paste is refused rather than stored. Describe the CAPABILITY you needed, never the person who needed it. Never report a security vulnerability here: email daniel@lucernanoetica.com.

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": {
      "want": "<want>"
    },
    "name": "report_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNo`missing` — no such verb, nothing to call. `wrong` — a door answered and the answer is not true. `poor` — it worked and the result was bad. Leave it off rather than guessing.
shopNothe shop you were working on, if there was one
verbNothe same thing as `surface`, by the word you probably reached for first
wantYesone sentence: what you were trying to do that this platform could not do, or did badly
surfaceNothe tool or verb you tried, if you know it — e.g. `front.set`, `checkout_intent`. `verb` works as a name for this too
answeredNowhat the door actually said, quoted short — the refusal text, the wrong value, or the thin result that was not good enough. The most useful field here.
expectedNothe acceptance line: what a correct answer would have looked like, concrete enough to check — e.g. 'the owner names a percentage and the shop’s cut on each seller sale becomes that number'
idempotency_keyNooptional, up to 64 characters: a retry with the same key is not counted twice. A signed-in caller gets the SAME receipt and ticket; an anonymous caller replays only a byte-identical filing

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "optional, up to 64 characters: a retry with the same key is not counted twice. A signed-in caller gets the SAME receipt and ticket; an anonymous caller replays only a byte-identical filing",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations (openWorldHint, write, non-idempotent) are far exceeded: the description discloses rate limits (50/24h signed-in, 10 per egress address anonymous), what happens over the cap, the two returned handles (`pg_…` ticket and `pr_…` receipt), that only the receipt's SHA-256 is stored and it is unrecoverable, privacy/redaction rules, deduplication behavior, and that a later partial report fills earlier blanks. Nothing here contradicts `idempotentHint: false` — the `idempotency_key` replay semantics are explained as the explicit exception rather than a denial of the annotation.

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?

Purpose and the three triggers are correctly front-loaded, and the FILE-IT-LIKE-A-SPEC guidance follows logically. However, the description runs several hundred words with heavy ALL-CAPS emphasis and repeats the privacy/verdict rules for `gap_check` and `gap_reply` across multiple paragraphs, which buries the operational core.

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 an 8-parameter write tool with no output schema, the description covers everything an agent needs: what gets returned (`pg_` ticket and `pr_` receipt), how to follow up, rate-limit and refusal behavior, idempotency semantics, and privacy/redaction constraints. The PII prohibition ('Do NOT send your human's brief') closes the main misuse risk for a free-text reporting tool.

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%, so the baseline is 3, and the description mostly restates field intent already present in the schema descriptions ('`want` is the one sentence', '`expected` is the acceptance line', '`answered` is WHAT THE DOOR ACTUALLY SAID, quoted short'). The value-add is emphasis rather than new meaning — the instruction to quote rather than characterize the refusal, and the 64-character cap on `idempotency_key` — but it does not clarify `shop`, `verb`/`surface` aliasing, or when to omit `kind` beyond what the schema already says.

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?

The opening line gives a specific verb and resource — 'FILE A TICKET on Lucerna itself — the platform's own homework list' — and immediately enumerates the three triggering conditions (missing/wrong/poor) that map to the `kind` enum. It is clearly distinguished from siblings like `gap_check`, `gap_reply`, SQL `upgrade.list`, and `modules.off`, so an agent can route correctly without opening the 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 when-to-file criteria are given ('a verb that does not exist', 'a door answered and its answer is not true', 'the RESULT was bad'), plus a named exclusion workflow: check `upgrade.list` and `modules.off` before claiming a verb is absent. It also states when NOT to use it ('Never report a security vulnerability here: email daniel@lucernanoetica.com') and routes follow-up to `gap_check`/`gap_reply`, which is the strongest possible routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources