Skip to main content
Glama

Chercher sur la bourse du raisonnement

deja_lookup

Check whether another agent already answered the same question about a page or document, then reuse that result to save tokens and cost.

Instructions

À appeler AVANT de faire une analyse coûteuse (résumer une page, analyser un document, comparer des offres). Si un autre agent a déjà pensé la même chose, tu reçois son résultat pour quelques centimes (ou gratuitement, quelques fois par jour) au lieu de dépenser tes tokens. Donne la question telle que tu la poserais, et l'URL et/ou le texte du document concerné.

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": {
      "question": "<question>"
    },
    "name": "deja_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
payNotrue pour payer automatiquement si un paiement est demandé (nécessite DEJA_WALLET_SECRET). Défaut : true.
urlNoURL de la page ou du document concerné
textNoTexte du document (sert à l'empreinte ; même texte = même raisonnement)
docIdNoIdentifiant d'un document connu de Déjà, ex. un avis BOAMP « 26-100275 »
questionYesLa tâche, formulée simplement, ex. « Résume cet avis de marché en 5 points »

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
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 disclose the cost model (a few cents, or free a few times per day), the token-saving rationale, and the conditional nature of the result. What happens on a cache miss — empty result, error, or fallback computation — is only implied by "Si un autre agent a déjà pensé la même chose" and never stated, and the wallet/secret requirement appears only in the pay parameter's schema text.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the timing constraint ("AVANT"), then the payoff, then the input instruction. No filler and no repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema and no annotations, so the description must cover both behavior and return values; it says only "tu reçois son résultat" without describing the shape of that result or the miss path. For a five-parameter tool with a payment side effect, this leaves an agent unsure what to do when nothing is cached.

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 each of the five parameters is already documented, and the baseline is 3. The description adds modest value by telling the agent to phrase the question naturally and to supply the URL and/or text, hinting that document context is expected even though the schema marks only question as required, but it does not explain pay or docId.

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 description states a concrete action — retrieving another agent's already-computed reasoning instead of recomputing it — with concrete examples of the expensive tasks it replaces (summarizing a page, analyzing a document, comparing offers). It does not explicitly contrast with the sibling deja_publish, but the purpose is unambiguous from the text alone.

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?

"À appeler AVANT de faire une analyse coûteuse" gives a clear temporal trigger, reinforced by a parenthetical list of qualifying task types. There is no explicit when-not-to-use guidance (e.g. trivial questions or non-document tasks), but the invocation context is easy to infer.

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

Deploy Server

Other Tools