Skip to main content
Glama
Sign In
Academic Writer MCP

Academic Writer MCP

by academic-writer-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Trouver des ouvrages par thème

find_works_by_topic
Read-onlyIdempotent

Search legal academic sources for real books and articles on a topic, ranked by relevance with access links, licenses, and pre-filled records. Returns results for the user to choose from.

Instructions

Trouve des livres, manuels et articles RÉELS sur un thème dans des bases légales (Internet Archive, DOAJ, arXiv, Crossref, Open Library), classés par pertinence, avec lien de consultation, licence et fiche pré-remplie. Aucune bibliothèque pirate. Présenter les résultats à l'utilisateur, qui choisit.

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": {
      "query": "<query>"
    },
    "name": "find_works_by_topic"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNobooks : Internet Archive, Open Library ; articles : DOAJ, arXiv, Crossref.all
limitNo
queryYesThème de recherche (ex. « нарезание зубчатых колес методом обката »). Essayer aussi la formulation en anglais pour plus de résultats.
languageNoLangue des livres (Internet Archive).
open_access_onlyNoSeulement les textes intégraux légalement téléchargeables.

Output Schema

NameRequiredDescriptionDefault
countYes
queryYes
worksYes
noticesYes
servicesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld and idempotent, so the safety profile is covered; the description adds genuinely new behavior: sources are restricted to legal databases, results are relevance-ranked, each carries a link and license, and the agent is expected to surface results rather than act on them. What is missing is any statement about coverage/latency tradeoffs or what happens when a source yields nothing, though the existing output schema partly compensates.

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 with the resource, the sources and the license guarantee front-loaded, followed by the safety exclusion and the presentation rule. No filler, though the capitalized 'RÉELS' and the source list in parentheses add minor noise.

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?

With five parameters at 80% schema coverage, a full annotation set and an output schema that handles return values, the description supplies everything still needed: which corpora, relevance ordering, legal-only constraint, and the expectation to hand results to the user for selection.

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 description coverage is 80%, so the schema itself already explains kind, query, language and open_access_only, including the hint to try English phrasing. The description adds no per-parameter meaning beyond what the schema documents; the only implicit mapping is that source selection drives the kind parameter, which the schema already spells out.

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 gives a specific verb ('Trouve') and a precisely bounded resource ('livres, manuels et articles RÉELS sur un thème'), and it names the exact corpora searched (Internet Archive, DOAJ, arXiv, Crossref, Open Library) plus the output shape (lien de consultation, licence, fiche pré-remplie). It never names or contrasts a sibling tool such as find_uncited_references or download_open_access, so an agent must infer the boundary itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Présenter les résultats à l'utilisateur, qui choisit' is a real workflow directive and 'Aucune bibliothèque pirate' implicitly rules out unauthorized sources. However, there is no explicit when-to-use/when-not guidance and no pointer to the sibling that handles downloading open-access full texts, leaving the handoff to later tools unstated.

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