Skip to main content
Glama

Axad

Say it aloud

speak
Idempotent

Make a natural voice recording of a sentence in the language the learner learns. Returns a link to the audio and the start and end time of each word. It spends a little credit; each recording is kept, so the same sentence again is free.

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": {
      "say": "<say>",
      "lang": "<lang>"
    },
    "name": "speak"
  }
}

Input Schema

NameRequiredDescriptionDefault
sayYes
langYes
voiceNoA speaker label of the language ("Vrouw", "Man"); omit for the narrator.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Goes beyond the annotations by disclosing cost ('spends a little credit') and cache semantics ('each recording is kept, so the same sentence again is free'), which usefully explains and reinforces idempotentHint=true. It also describes the return payload (audio link plus per-word start/end times) in the absence of an output schema. It does not say how much credit is spent or whether syntactically different but equivalent sentences hit the cache.

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

Conciseness5/5

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

Three short sentences, ordered purpose → return value → cost/caching, with no filler. Each sentence contributes information an agent would otherwise have to guess.

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 3-parameter tool with no output schema, the description covers the essentials: what it produces, what comes back, and the cost/caching model. The remaining gap is the format of 'lang' and the practical size limit on 'say', which an agent could only discover by trial.

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 coverage is only 33%, and only 'voice' carries a schema description. The description compensates partially by framing 'say' as a sentence and 'lang' as the language the learner learns, but it never states the expected language format (code vs. name) or notes the 600-character cap on 'say'.

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 concrete verb and resource: produce a voice recording of a sentence in the learner's target language. That is unambiguous and clearly distinct from the lesson-content siblings (show_*, list_*, review_card). It stops short of explicitly naming any alternative, but the purpose itself is fully legible.

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 is only implied: you record a sentence in the language being learned. There is no statement of when to reach for this versus the many show_* content tools, nor any exclusions or prerequisites. The caching note hints at a workflow (repeat calls are free) but is not framed as guidance.

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.