Skip to main content
Glama

Update Question

update_question
DestructiveIdempotent

Update an existing question's statement, solution, or difficulty level; omitted fields stay unchanged, and students see edits immediately without grade changes.

Instructions

Corrige el enunciado, la solución o la dificultad de una pregunta existente (lo omitido no cambia).

Reemplaza el texto completo del campo: parte del valor actual (get_test) y conserva saltos de línea e indentación del código. Los alumnos ven el cambio de inmediato; las notas no cambian.

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_id": "<question_id>"
    },
    "name": "update_question"
  }
}

Input Schema

NameRequiredDescriptionDefault
difficultyNo
question_idYes
question_textNo
step_by_step_solutionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnly=false, destructive=true, idempotent=true; the description goes well beyond that by explaining overwrite semantics ('Reemplaza el texto completo del campo'), the propagation effect ('Los alumnos ven el cambio de inmediato'), and a scoped side-effect guarantee ('las notas no cambian'). It also flags formatting risk (line breaks and code indentation must be preserved), which is exactly the operational caveat a destructive editor needs and which no annotation conveys.

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?

Front-loaded with the verb and the scope, then a second paragraph of operational details — no filler or restatement of the tool name. The parenthetical get_test reference and the mid-sentence line break make it slightly denser to parse than necessary, but each sentence contributes a distinct fact.

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?

For a destructive field-overwriting mutation with an output schema available, the definition covers the risky parts: partial update, full text replacement, formatting preservation, immediate student visibility, and unaffected grades. Remaining gaps are minor — permission requirements and behavior when question_id does not exist are not addressed, but return values need not be described since an output schema exists.

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?

With 0% schema description coverage, the description must carry the meaning, and it maps three of the four parameters to concrete concepts (enunciado=question_text, solución=step_by_step_solution, dificultad=difficulty) while implying question_id as the required target. It adds the crucial full-replacement-vs-omitted distinction and formatting expectations; it does not explicitly resolve whether a null value behaves like omission, which the schema's null defaults leave ambiguous.

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?

States a specific verb plus resource: 'Corrige el enunciado, la solución o la dificultad de una pregunta existente' — it names the exact fields it mutates and the object type (an existing question), which separates it from create/append-style siblings. The parenthetical '(lo omitido no cambia)' immediately scopes the operation as partial-update, so an agent knows precisely what it does without opening the schema.

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 clear operating context: use it only on existing questions, treat unspecified fields as untouched, and read the current value via get_test before editing. It stops short of explicit exclusions (e.g. what to do for new questions or bulk rewrites), but the workflow and the read-then-write pattern are spelled out rather than inferred.

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