Skip to main content
Glama

Estimate speech time

estimate_speech_time
Read-onlyIdempotent

Use this when the user wants to know how long a speech or script will take. Accepts a script up to 30,000 characters or a word count, and slow, conversational, presentation, fast, or a whole number from 60 to 300 words per minute. Returns a duration table; script sections begin at blank lines or heading lines. [PAUSE] adds one second and [PAUSE 3] adds three seconds; numeric cues accept whole seconds from 1 to 86,400 per cue. Does not measure a live recording.

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": "estimate_speech_time"
  }
}

Input Schema

NameRequiredDescriptionDefault
speedNoOptional named pace or whole number from 60 to 300 wpm, e.g. presentation. The result also shows the four named paces.
scriptNoScript to time, e.g. Hello everyone. [PAUSE 2] Thank you for coming.
word_countNoUse when no script is available: spoken word count, e.g. 650.

Output Schema

NameRequiredDescriptionDefault
timingsYes
durationYes
sectionsYes
speed_wpmYes
word_countYes
duration_msYes
pause_secondsYes
section_countYes
selected_speedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, so the description correctly spends its budget on behavior: the duration-table return, the blank-line/heading sectioning rule, and the [PAUSE]/[PAUSE N] semantics with their 1–86,400 second bounds. What's missing is only minor edge behavior such as precedence between script and word_count.

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 trigger, then limits, pace options, return shape, and pause syntax — each sentence carries information. It runs five dense sentences, so it is near the ceiling but not bloated.

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?

An output schema exists, so return values need not be detailed, yet the description already flags a duration table. Coverage is nearly complete apart from the script-versus-word_count precedence rule and the lack of explicit sibling routing.

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 already 100%, so baseline is 3; the description earns extra credit by explaining semantics the schema does not, notably that script sections are split at blank or heading lines and how pause cues are parsed and clamped.

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?

States a specific verb+resource ('how long a speech or script will take') and clearly separates the two accepted inputs. It never names plan_script_length or show_teleprompter, so sibling differentiation has to be inferred from scope rather than read off the text.

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?

Opens with the triggering condition ('when the user wants to know how long a speech or script will take') and adds a genuine exclusion: 'Does not measure a live recording.' It stops short of routing between siblings or saying which of script vs word_count wins if both are supplied.

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