Skip to main content
Glama

Кто встал

stuck_students
Read-onlyIdempotent

Ученики, которые не дошли до конца и ничего не делали дольше days дней (ни входа, ни пройденного урока). Это адрес для куратора, а не оценка ученика. cohort_id сужает до одного потока; без него — вся школа, включая записи без потока. Черновики курсов не считаются.

Сверху те, кто молчит дольше всех, в конце те, кто не заходил ни разу. За раз просматривается не больше 200 записей: total показывает, сколько всего записей без активности, в том числе дошедших до конца. Дошедшие в students не попадают, поэтому там бывает меньше limit. Читайте дальше с offset=next_offset, пока он не станет null.

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": "stuck_students"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
limitNo
offsetNo
cohort_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 50,
      +  "title": "Limit",
      +  "type": "integer"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "title": "Offset",
      +  "type": "integer"
      +}
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, non-destructive, idempotent and closed-world, so safety is covered. The description goes notably beyond that with result ordering ('Сверху те, кто молчит дольше всех'), a 200-record per-view cap, and the caveat that `total` counts all inactive records including finishers while `students` may hold fewer than `limit` rows. However, it does not indicate what fields each student record carries or whether defaults (days=7, limit=50) have meaningful side effects.

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?

The definition is front-loaded with the returned set before scope and pagination details, and every sentence adds operational value. It is a dense multi-sentence block with the pagination rules packed into one paragraph, which is slightly harder to scan than necessary but not padded.

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?

For a four-parameter read tool with no output schema and 0% schema coverage, the description covers scope, ordering, the 200-record view cap, `total` semantics and pagination thoroughly. It stops short of describing the shape of each returned student record or the default values, which an agent may need to interpret results correctly.

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 0%, so the description must compensate; it partially does -- `days` is implicitly defined as a day threshold, `cohort_id` gets clear semantics including the null case, and pagination via `offset=next_offset` is spelled out. `limit` is only alluded to through the 200-record cap and `offset` only through `next_offset`, leaving the four parameters without complete coverage.

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 first sentence defines the returned set precisely: students who did not finish and have shown no activity (no login, no completed lesson) for more than `days` days. It adds a framing statement ('это адрес для куратора, а не оценка ученика'), but never contrasts the tool with the closest sibling, cohort_progress, so the agent must infer the boundary from behavior alone.

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 states the effect of `cohort_id` (narrow to one cohort) versus omitting it (the whole school, including records with no cohort) and notes that course drafts are excluded, which is exactly the kind of scope guidance an agent needs. It lacks explicit when-not-to-use or a named alternative, so it falls short of a 5.

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