Skip to main content
Glama
Podcast MCP
by calebn

hear_session_suggestion_tool

Preview a pending session suggestion by listening to current, suggested, or A/B audio before accepting it, without changing the project.

Instructions

Hear a pending session before accepting it: the place as it is, after accepting, or both.

mode: current (the window as it is), suggested (the same window after accept_session_suggestion_tool, take_index chosen as there) or ab (current, a gap, then suggested; the default). pad_sec is the audio kept each side of the change (0 to 10 s, else pad_sec_invalid) and gap_sec the silence between A and B (0 to 5 s, else gap_sec_invalid). Nothing in the project, its history or the session changes, and a replace that would remove another track's speech still plays; the result's speech names the words. Refuses what accepting refuses, with the same codes: a session that is not pending, a range or insert point that changed (stale_anchor), an unknown take (take_not_found), a take_index on an insert (take_not_applicable), a track the take did not record (track_not_recorded) and pending edits inside the range (pending_edits_in_range). dry_run renders the WAVs without playing.

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": {
      "suggestion_id": "<suggestion_id>"
    },
    "name": "hear_session_suggestion_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoab
dry_runNo
gap_secNo
pad_secNo
rerenderNo
take_indexNo
project_pathNo
suggestion_idYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.4

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the load and does well on safety: it states that nothing in the project, history, or session changes, that a speech-removing replace still plays, and it enumerates the exact refusal codes (stale_anchor, take_not_found, take_not_applicable, track_not_recorded, pending_edits_in_range, pad_sec_invalid, gap_sec_invalid). The lower score reflects gaps rather than contradictions: rerender and project_path behaviors, and the fact that hearing actually plays audio to the user's device, are never disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence is front-loaded and effective, but the body is one sprawling block mixing mode semantics, numeric bounds, error codes, and non-destructiveness with hard line breaks mid-thought. The clause 'the result's speech names the words' is compressed to the point of opacity and forces a re-read.

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 an 8-parameter audio-preview tool, the definition covers the audition semantics, non-destructiveness, refusal parity with accept_session_suggestion_tool, and dry-run mode, and an output schema exists so return values need no explanation. Only rerender and project_path are unaddressed, which is a minor residual gap rather than a blocker.

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 0%, so the description must compensate, and it does for mode (with all three values defined), pad_sec (0-10 s with its error code), gap_sec (0-5 s with its error code), take_index (meaningful only in suggested mode), and dry_run. Two of eight parameters, rerender and project_path, are left entirely unexplained, so compensation is substantial but incomplete.

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?

Opens with a specific verb and object: hear a pending session suggestion before accepting it, with the three audition modes (current, suggested, ab) spelled out. It is clearly distinguishable from accept/skip siblings, though the phrase 'the place as it is' is idiomatic rather than precise about what audio source is played.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by 'before accepting it' and by dry_run rendering WAVs without playing, which tells an agent it can preview offline. However, there is no explicit statement of when to prefer this over list_session_suggestions_tool or get_session_state_tool, nor when to skip hearing and accept directly.

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