Skip to main content
Glama

Gridbert

compile_done

Meldet ein Inbox-Item als fertig eingearbeitet (nach compile_next + upsert_page). keys = die Seiten, in die der Inhalt eingearbeitet wurde; jede muss einen [quelle: <item_id>]-Anker tragen, dessen Werte wörtlich in der Quelle stehen — der Server prüft das automatisch. keys=[] heißt: nichts Verwertbares, nichts einzuarbeiten. Für jede Seite ohne Typ typing[key] = { type, status, relations, confidence } angeben, ausschließlich mit dem Vokabular aus dem tbox-Feld der letzten compile_next-Antwort. claim_token aus compile_next.item.claim_token UNVERÄNDERT zurückgeben — er beweist, dass das Item noch dir gehört (sonst lease_lost = die Sperre ist abgelaufen).

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_id": "<item_id>",
      "keys": "<keys>"
    },
    "name": "compile_done"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYesSeiten-Keys, in die eingearbeitet wurde; [] = nichts Verwertbares.
typingNoTyping je noch untypisierter Ziel-Seite: { "<key>": { "type": "<T-Box-Typ|null>", "status": "<status|null>", "relations": { "<prädikat>": ["<key>"] }, "confidence": 0..1 } }.
item_idYesDie Item-ID aus compile_next.
claim_tokenNoSperr-Schlüssel aus compile_next.item.claim_token — unverändert zurückgeben.

Output Schema

NameRequiredDescriptionDefault
okYesimmer true. Fehler kommen als isError ohne structuredContent zurück (errors.error_result: {ok:false, error_class, fehler}).
toolYesName des proxierten Vault-Tools.
resultYesRohes MCP-Tool-Result der Instanz: {content: [...], isError: bool}. Der eigentliche Inhalt steckt als JSON-Text in content[0].text.
hinweisNoOptionaler Hinweis ans Modell (F14) — Datenstand-Warnung, nächster Schritt, Granularitäts-Caveat. Darf null sein.
proxiedYesimmer true — die Nutzlast kommt aus der engram-Instanz, nicht aus dem Gateway.
workspaceNoNur bei Berater-Accounts: der Arbeitsbereich, in dem dieser Call gelandet ist (dispatch.py stempelt ihn zentral an JEDES Result). Haushalts-Results tragen das Feld nicht.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / claim_token / description
      Previous value: -"Fencing-Token aus compile_next.item.claim_token — unverändert zurückgeben."New value: +"Sperr-Schlüssel aus compile_next.item.claim_token — unverändert zurückgeben."
    • changedInput schema / properties / item_id / description
      Previous value: -"Das geclaimte Inbox-Item (aus compile_next)."New value: +"Die Item-ID aus compile_next."
    • changedInput schema / properties / keys / description
      Previous value: -"Ziel-Seiten-Keys des Merges; [] = Noise."New value: +"Seiten-Keys, in die eingearbeitet wurde; [] = nichts Verwertbares."
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the safety profile is covered. The description adds substantial context beyond that: the server auto-verifies [quelle: <item_id>] anchors verbatim against the source, and a stale claim_token yields lease_lost. It does not explain the response body, but an output schema exists.

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?

Dense but front-loaded: the primary action comes first, followed by keys rules, typing rules, and the claim_token constraint. Every clause carries a real constraint, though the run-on sentence structure is heavier than ideal.

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 workflow-finalization mutation with an output schema, the description covers preconditions, the empty-result case, server-side validation, the typing vocabulary source, and the lease-expiry failure mode. Nothing essential for correct invocation is missing.

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 baseline is 3; the description nonetheless adds real meaning over the schema: keys must each carry an anchor whose values appear verbatim in the source (server-enforced), keys=[] has a defined semantics, typing must use only tbox vocabulary from the last compile_next response, and claim_token must be returned unchanged as proof of lease ownership.

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 a specific action and resource: marks an inbox item as fully processed. It explicitly positions itself in a workflow (after compile_next + upsert_page) and names those siblings, so an agent can distinguish it from upsert_page and compile_next without opening schemas.

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?

Gives the exact precondition (only after compile_next + upsert_page) and a clear edge-case rule (keys=[] means nothing usable). The relationship to the sibling tools is spelled out rather than left to inference.

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