Skip to main content
Glama
Sign In
Academic Writer MCP

Academic Writer MCP

by academic-writer-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Rechercher des livres et articles

search_sources
Read-onlyIdempotent

Search real books and articles across Google Books, OpenAlex, and Crossref to retrieve pre-filled source records for user confirmation before saving.

Instructions

Cherche des ouvrages et articles RÉELS dans Google Books (livres, dont russes), OpenAlex et Crossref. Renvoie des fiches pré-remplies à présenter à l'utilisateur ; n'enregistrer (register_source) que celles qu'il confirme. Mode connecté uniquement ; seuls les termes de recherche sont envoyés.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_sources"
  }
}

Input Schema

NameRequiredDescriptionDefault
isbnNo
kindNobooks : Google Books ; articles : OpenAlex + Crossref ; all : tous.all
limitNo
queryNoTitre ou mots du titre (russe, français, anglais).
authorNoNom de famille d'un auteur (facultatif).

Output Schema

NameRequiredDescriptionDefault
queryYes
noticesYes
servicesYesServices interrogés.
candidatesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, open-world behavior, so the description is not needed for the safety profile. It still adds real value beyond them: the tool queries live external services, returns unsaved draft records rather than persisted sources, requires a connected session, and transmits only the search terms — a useful privacy and side-effect note.

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?

Three short sentences, front-loaded with what is searched and where, followed by the result-handling rule and the connectivity constraint. No filler, though the parenthetical about Russian books is only marginally relevant to invocation.

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?

An output schema exists so return values need not be described, and the description covers the remaining essentials for a five-parameter, zero-required, read-only search: sources queried, draft-vs-saved semantics, follow-up tool, and the connected-mode requirement. Nothing critical for correct invocation is absent.

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 60%: kind, query and author are already documented in the schema, but isbn and limit are not. The description does not explain that isbn performs a direct identifier lookup or that limit is capped at 10, so it adds little parameter meaning beyond what the schema supplies.

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 description states a specific verb (chercher) and resource (ouvrages et articles réels), names the concrete backends (Google Books incl. Russian titles, OpenAlex, Crossref), and implicitly separates the search action from the sibling register_source. An agent can distinguish it from search_in_documents because the scope is external catalogs, not local document content.

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?

It gives explicit workflow guidance: results are pre-filled cards to show the user, and only user-confirmed items should be passed to register_source. It also states a precondition (mode connecté uniquement). It does not contrast against other search entry points such as search_in_documents or import_sources_file, so it stops short of full alternative routing.

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