Skip to main content
Glama

Confirmer une vérification manuelle

confirm_source_verification

Marks a source as manually verified after the user locates it, records where they found it, and applies the status only on explicit confirmation.

Instructions

Marque une source « vérifiée manuellement » après que l'utilisateur l'a trouvée lui-même (par exemple via les liens manual_links de la fiche). N'appeler QUE sur confirmation explicite de l'utilisateur.

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": {
      "source_id": "<source_id>",
      "where": "<where>"
    },
    "name": "confirm_source_verification"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
whereYesOù l'UTILISATEUR a trouvé la source : « РГБ », « eLIBRARY », « bibliothèque СТАНКИН », « exemplaire papier »…
source_idYes

Output Schema

NameRequiredDescriptionDefault
idYes
keyYesClé de citation stable, utilisée dans le texte : [@clé] ou [@clé, с. 15].
dataYes
originYes
project_idYes
document_idNo
source_typeYes
verified_atNo
manual_linksNoLiens de vérification à ouvrir par l'utilisateur dans son navigateur.
status_labelYes
citation_countNo
verification_statusYes
verification_detailsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare a non-destructive write (readOnlyHint=false, destructiveHint=false), so the description's added value is the explicit-confirmation requirement and the meaning of 'manually verified'. With idempotentHint=false, an agent would benefit from knowing what a repeated call does or whether the status change is reversible, and that is not stated.

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?

Two sentences, zero padding, with the state change and the usage restriction both front-loaded. The parenthetical example of where the user might have found the source earns its place by clarifying the 'where' concept.

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?

An output schema exists, so return values need no explanation, and the annotations carry the safety profile. However, for a three-parameter mutation with only 33% schema coverage, the definition leaves source_id and note semantics and repeat-call behavior undefined, which is a real gap for an agent invoking it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%: 'where' is documented in the schema, but source_id and note are bare. The description mentions manual_links as a context for 'where' but adds nothing about the format or origin of source_id, nor what the optional note is used for, so the coverage gap is not compensated.

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?

States a specific verb and resource ('marque une source vérifiée manuellement') plus the crucial qualifier that the user found the source themselves, which distinguishes this human-confirmation path from automated verification siblings. It does not name any sibling tool explicitly, so an agent must infer the contrast with tools like verify_source_metadata.

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?

Gives a hard gating rule: call ONLY on explicit user confirmation, and indicates the typical discovery path (manual_links on the record). It sets the when clearly but offers no when-not or named alternative for cases where verification should be automatic instead.

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