Skip to main content
Glama
nmbrthirteen

podcli

by nmbrthirteen
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

suggest_clips

Submit analyzed viral clip moments with timestamps and hooks for user review. Stores suggestions, assigns clip numbers, and pushes them to the Web UI for approval before export.

Instructions

STEP 2 — Submit your clip suggestions after analyzing the transcript.

Before calling this: read the transcript via get_ui_state(include_transcript: true) and identify the best viral moments.

Every suggestion must carry its own context. A clip that opens on an answer whose question stayed behind the cut is rejected: widen start_second so the question is inside the clip.

What it does: Stores your suggestions, assigns clip numbers (#1, #2, etc.), and pushes them to the Web UI for the user to review.

After this: the user reviews in the UI. Then export with batch_create_clips(export_selected: true) or create_clip(clip_number: N).

Input Schema

NameRequiredDescriptionDefault
suggestionsYesArray of suggested clip moments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.8.0
    • addedInput schema / properties / suggestions / items / properties / hook
      Added value: +{
+  "description": "Opening hook: a 1-15s passage from inside the clip, played before the clip. It must be a line actually spoken inside the clip's range (or its segments), never invented text.",
+  "properties": {
+    "end": {
+      "description": "Hook end in seconds, on the source clock",
+      "type": "number"
+    },
+    "mode": {
+      "description": "repeat: the passage plays first and again in place. move: it plays first and is cut from its place.",
+      "enum": [
+        "repeat",
+        "move"
+      ],
+      "type": "string"
+    },
+    "start": {
+      "description": "Hook start in seconds, on the source clock",
+      "type": "number"
+    }
+  },
+  "required": [
+    "start",
+    "end",
+    "mode"
+  ],
+  "type": "object"
+}
  2. Changed13 schema fields changedv2.7.3
    • addedInput schema / properties / suggestions / items / properties / content_type / description
      Added value: +"Content classification: guest_story, technical_insight, market_landscape, business_strategy, hot_take"
    • addedInput schema / properties / suggestions / items / properties / context_line
      Added value: +{
+  "description": "The question or setup that makes the clip land, in one line, for an editor to place. Nothing renders it yet, so it does NOT satisfy the standalone check: the clip range itself must still contain the setup.",
+  "type": "string"
+}
    • addedInput schema / properties / suggestions / items / properties / end_second / description
      Added value: +"End timestamp in seconds"
    • addedInput schema / properties / suggestions / items / properties / payoff
      Added value: +{
+  "description": "What the viewer walks away with. One sentence, second person, e.g. \"You learn why raising a seed round early cost them control of pricing.\" Not a description of the clip and not a restatement of the title.",
+  "type": "string"
+}
    • addedInput schema / properties / suggestions / items / properties / preview_text / description
      Added value: +"The first sentence or two the viewer actually hears, verbatim from start_second. This is what the standalone check reads, so it has to be the real opening line, not a paraphrase."
    • addedInput schema / properties / suggestions / items / properties / reasoning / description
      Added value: +"Why this earns 30 seconds of a stranger's attention"
    • addedInput schema / properties / suggestions / items / properties / score / description
      Added value: +"Virality score (0-20). Sum of standalone + hook + relevance + quotability (each 1-5)."
    • changedInput schema / properties / suggestions / items / properties / segments / description
      Previous value: -"Multi-cut keep-ranges. Omit for a single continuous clip."New value: +"Multi-cut keep-ranges within the clip. Use to cut out filler/tangents in the middle. Omit for a single continuous clip."
    • addedInput schema / properties / suggestions / items / properties / standalone
      Added value: +{
+  "description": "What a viewer who never heard this episode must already know to follow the clip. Write \"nothing\" when the clip carries its own setup.",
+  "type": "string"
+}
    • addedInput schema / properties / suggestions / items / properties / start_second / description
      Added value: +"Start timestamp in seconds. If the moment is an answer, move this back to include the question that prompted it."
    • addedInput schema / properties / suggestions / items / properties / suggested_caption_style / description
      Added value: +"Recommended caption style for this clip"
    • addedInput schema / properties / suggestions / items / properties / title / description
      Added value: +"Short catchy title for the clip"
    • changedInput schema / properties / suggestions / items / required
      Previous value: -[
-  "title",
-  "start_second",
-  "end_second",
-  "reasoning"
-]New value: +[
+  "title",
+  "start_second",
+  "end_second",
+  "payoff",
+  "standalone",
+  "reasoning",
+  "preview_text"
+]
  3. Changed3 schema fields changedv2.7.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / suggestions / items / additionalProperties
      Removed value: -false
    • removedInput schema / properties / suggestions / items / properties / segments / items / additionalProperties
      Removed value: -false
  4. First observedv2.0.0

TDQS

A4.5/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It does disclose real behavior: suggestions are stored, numbered, and pushed to the Web UI for human review, and the flow is gated by prior transcript analysis. It does not state whether repeat calls overwrite prior suggestions, whether a transcript must already exist, or what happens on rejection, which keeps it short of 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?

Front-loaded with the workflow stage, then cleanly segmented into 'Before calling this', 'What it does', and 'After this'. Every sentence is functional, though the opening line and the 'What it does' line partially restate each other, so it is tight rather than maximally economical.

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 tool whose single parameter is a deeply nested object with many required fields, the description supplies the pipeline position, the content-quality constraint, and the export handoff, which is the information an agent cannot derive from the schema. Return values are not explained (no output schema), but the assigned clip numbering is covered, leaving only overwrite/idempotency behavior unaddressed.

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 description coverage is 100%, so the baseline is 3 and the schema already documents fields like payoff, standalone, preview_text, and hook. The description still adds validation semantics the schema does not enforce: every suggestion must carry its own context, and a clip opening on an answer whose question was cut is rejected. That rule-level guidance lifts it above baseline.

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 and resource — submit/store clip suggestions — and elaborates with concrete effects: assigns clip numbers (#1, #2), pushes them to the Web UI. It is clearly distinguishable from siblings like create_clip and batch_create_clips, which it names as the downstream export step.

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?

Explicitly states the prerequisite (read the transcript via get_ui_state(include_transcript: true) and identify viral moments), the ordering (STEP 2, after analysis), and the follow-up path (batch_create_clips(export_selected: true) or create_clip(clip_number: N)). It even encodes a rejection rule with the corrective action (widen start_second so the question is inside the clip).

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