Skip to main content
Glama

FișaEdu – fișe de lucru

Programa școlară pe FișaEdu

programa
Read-onlyIdempotent

Temele din programa școlară românească pentru o grupă/clasă și o materie, cum sunt organizate pe FișaEdu (capitole și teme), fiecare cu linkul paginii cu fișe. Folosește-l ca să propui teme potrivite pentru o clasă („ce se face la matematică în clasa a 2-a?”) sau înainte de cauta_fise, când cererea e vagă. Fără materie, întoarce materiile clasei și câteva teme din fiecare. List Romanian national-curriculum topics for a grade (and optional subject), with links to the FișaEdu topic pages.

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": {
      "grade": "<grade>"
    },
    "name": "programa"
  }
}

Input Schema

NameRequiredDescriptionDefault
gradeYesGrupa sau clasa (obligatoriu): "grupa mare", "pregătitoare", "clasa a 2-a", "2"… Numeric: -3..-1 grădiniță, 0 pregătitoare, 1–12.
subjectNoMateria / subject, în română sau engleză: "matematică", "limba română", "engleză", "științe", "math"…

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds genuine behavioral detail beyond that: the fallback shape when no subject is supplied (returns the grade's subjects plus a few topics from each) and the fact that returned topics carry page links. Pagination/volume limits are not stated, keeping it below a 5.

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?

Content is front-loaded: what the tool returns, then when to call it, then the omission fallback. The Romanian sentence is followed by an English restatement, which is mildly redundant but justified for cross-language agent routing; no sentence is filler.

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

Completeness4/5

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

With only two parameters, full schema coverage, and rich annotations, the definition covers purpose, routing, fallback behavior, and return organization (chapters, topics, links). There is no output schema, so the exact response envelope (field names, whether links are absolute, topic counts) is still implicit, but the description is sufficient to call the tool correctly.

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 the baseline is 3, and the description earns an extra point by documenting what happens when the optional subject parameter is omitted — behavior the schema cannot express. The grade parameter's numeric range mapping stays entirely in the schema, so nothing further is added there.

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 names a concrete resource (Romanian national-curriculum topics for a grade/subject), explains how it is structured on FișaEdu (chapters and topics, each with a worksheet-page link), and summarizes the same scope in English. It is clearly distinguishable from the retrieval siblings cauta_fise and detalii_fisa.

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?

It gives explicit when-to-use conditions: to propose suitable topics for a class (with an example query, "ce se face la matematică în clasa a 2-a?") and as a precursor to cauta_fise when the request is vague. That names both the trigger and the alternative tool, leaving nothing 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