Skip to main content
Glama

Set a pronunciation

pronunciations_upsert

[writes flayr data · write scope] Sets how voices say term for a brand: sayAs is a plain respelling (e.g. "Dahss-tuhl"). Updates the entry with that term (case-insensitive; accepts a waiting suggestion) or creates one; fields left out keep their values. acceptedHearings are transcriptions Verify also counts as a pass. Applies to every voice from the next render, with no per-call setup. (Wraps POST /api/v2/pronunciations/upsert.)

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": {
      "term": "<term>",
      "sayAs": "<sayAs>"
    },
    "name": "pronunciations_upsert"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNo
termYes
sayAsYes
brandIdNoBrand id, or `personal`.
alsoRecordNoAlso tell a human voice actor (default true).
spellExactNoRead it letter by letter.
acceptedHearingsNoTranscriptions Verify also counts as a pass.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare the write, non-destructive, non-idempotent, closed-world profile. The description adds real value beyond that: the required `write` scope, partial-merge semantics ('fields left out keep their values'), and propagation timing ('applies to every voice from the next render'). It does not mention the side effect that alsoRecord defaults to true and notifies a human voice actor, nor what the call returns.

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 scope marker and the core action, then the upsert semantics, then side effects on renders. Dense but every clause carries information; the trailing endpoint parenthetical is the only near-disposable element.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 7-parameter mutation tool with no output schema needs to cover more than this. Core semantics, scope, and propagation are handled well, but the description is silent on the human-voice-actor side effect (alsoRecord), the `note` field, `spellExact`, and what a caller gets back, leaving gaps for an agent deciding whether the call is safe to repeat.

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?

It adds genuine meaning for `sayAs` (a plain respelling, with a 'Dahss-tuhl' example) and for `term` as a case-insensitive matching key, which the schema does not state. With 57% schema description coverage, the remaining parameters — note, alsoRecord, spellExact, brandId defaults — get no treatment in the description, so it neither compensates fully nor is redundant.

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 — it sets how voices say a `term` for a brand — plus the upsert scope (updates an existing entry or creates one). An agent can distinguish this from pronunciations_list and pronunciations_verify without opening any schema, and the `sayAs` example makes the resource concrete.

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?

Explains the key selection logic: matching is case-insensitive, a waiting suggestion can be accepted, and fields left out keep their values. It implies the write path (versus list/verify) but never explicitly says when to call this instead of pronunciations_verify or pronunciations_list, so no true exclusion statement is present.

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