Skip to main content
Glama

Bettyapp for Teachers

Find lecture clips to teach a topic

search_teaching_clips
Read-onlyIdempotent

Finds the few minutes inside real lectures where a teacher explains a topic, for a teacher planning a class, by the topic's name and the class's Level. Typical requests it serves: "a few minutes of a lecture on the chain rule for my Grade 12 class", "a concrete example of entropy for first-year chemistry". Example: the chain rule returns MIT 18.01 Lecture 04 from 28:03 to 33:44 of the 46-minute lecture. recommended: clips judged to teach the topic, best first. fallback: when too few are recommended, related moments with their fallback_reason, not teaching clips. Neither: Bettyapp has no lecture on it. Each clip has its clip_id, lecture, start_seconds, suggested_end_seconds, curriculum place, play_url, classroom_share_url, credit line and licence note. teaching.role (teaches, uses or mentions) and teaching.depth (0, named only, to 3, a thorough treatment) say how an AI review of the transcript judged the moment (judged_by "ai_transcript_review"; not_judged where none was made).

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": {
      "topic": "<topic>",
      "age_group": "<age_group>"
    },
    "name": "search_teaching_clips"
  }
}

Input Schema

NameRequiredDescriptionDefault
topicYesThe topic's name, as a teacher says it in a lecture: one to four words, for example "mitosis" or "chain rule", not the whole request "a short clip on mitosis for my grade 10 class".
languageNoOnly lectures spoken in this language, as its code: en, es, pt. Without it, every language.
age_groupYesThe age group of the students the class is for: child (under 13), teen (13 to 17) or adult (18 and over). Bettyapp gives clips from lectures that suit the age.
max_resultsNoHow many clips, 1 to 10.
curriculum_codeNoA course or syllabus place the class follows, as a study guide gives them: a section code ("B2.1", "4.4.1") or a course with it ("SPH4U B2.1"). A clip in it comes first among clips alike.
education_levelNoThe class's Level: elementary (Elementary (K–5)), middle_school (Middle School (6–8)), high_school (High School (9–12)), university_year1 (Year 1 University), university_upper (Upper Year University), graduate (Graduate & Professional). A clip at this Level comes first among clips alike; without it, every Level.
target_duration_secondsNoAbout how long a clip the teacher wants, in seconds: among clips alike, the nearer length comes first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnly/idempotent/closed-world annotations, the description discloses the ranking contract ('best first'), the fallback contract (related moments flagged with fallback_reason, and explicitly 'not teaching clips'), the empty-result case, and the provenance of teaching.role and teaching.depth as an AI transcript review with a 0-3 depth scale. That is substantial behavioral context an agent could not get from annotations or schema.

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?

Purpose is front-loaded, then examples, then result tiers, then return fields, which is a sensible order given there is no output schema. The prose is dense and fragmentary in places ('Neither: Bettyapp has no lecture on it.') and the long field enumeration runs together, but no sentence is purely filler.

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 no output schema, the description carries the return-value burden and does so by listing clip_id, start_seconds, suggested_end_seconds, play_url, classroom_share_url, credit and licence, plus the role/depth judgment fields. Combined with the tier semantics and the 100%-covered input schema, an agent has enough to call it and interpret results.

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 100%, so every one of the 7 parameters is already fully explained, including the enum meanings and the tie-breaking behavior of curriculum_code and education_level. The description only restates 'by the topic's name and the class's Level' and adds no syntax, format, or edge-case meaning beyond the schema, so baseline 3 applies.

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 gives a specific verb and resource: 'Finds the few minutes inside real lectures where a teacher explains a topic', scoped by topic name and class Level. It is clearly a topic-based clip search rather than a curriculum lookup or clip fetch, but it never names a sibling tool to sharpen that boundary (find_by_curriculum, get_clip), which keeps it at 4 rather than 5.

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 supplies two concrete request phrasings ('a few minutes of a lecture on the chain rule for my Grade 12 class', 'a concrete example of entropy for first-year chemistry') that tell an agent exactly what kind of ask belongs here, plus the outcome tiers recommended/fallback/none. It stops short of stating when NOT to use it or which sibling handles the alternative cases.

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