Skip to main content
Glama

Correct a song’s brief

edit_song_brief
Idempotent

Rewrite what the song is about, in the user’s words The brief (get_song: brief) is what every director reads before making anything for the song: its theme, the story under it, how the feeling moves through its sections (mood_arc), the setting it evokes and its tone. When it reads the song wrong ("it’s about my father, not a breakup"), send the fields to change; the others stay. mood_arc replaces the whole list (a section with an empty feeling is dropped); null or "" clears tone, story or setting; theme can’t be emptied. Plain text, on one line each. The correction is the user’s: brief.edited is true, every video, Canvas and cover made from then on reads it, and nothing replaces it (new lyrics or a new analysis keep it) until rewrite_song_brief. 409 while a song without a brief yet is sent no theme.

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": {
      "song_id": "<song_id>"
    },
    "name": "edit_song_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNoIts register, in a few words (tender, comic parody, defiant…)
storyNoThe story or situation under the words: who it is about, what happens
themeNoWhat the song is about, in a sentence
settingNoAn era, a place or a scene it evokes
song_idYesThe song id
mood_arcNoHow the feeling moves through the song, section by section: replaces the whole list

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) it discloses field-level effects the annotations cannot: mood_arc replaces the whole list and empty-feeling sections are dropped, null or "" clears tone/story/setting, theme cannot be emptied, and brief.edited becomes true. It also describes persistence (new lyrics or a new analysis will not replace it until rewrite_song_brief) and the 409 failure case for a song with no brief yet.

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?

The most important information (the verb, the partial-update rule, the clearing rules) is front-loaded and there is little filler. It is dense, with some long run-on sentences and a missing period after "in the user's words," which slightly hurts scannability but not comprehension.

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

Completeness5/5

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

For a mutation tool with six optional fields, no output schema, and downstream consumers (videos, Canvas, covers), the description covers what changes, what persists, what is irreversible (theme cannot be emptied), and the 409 precondition. An agent has enough to call it correctly without further probing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so the baseline is 3, but the description adds semantics the schema does not carry: the differing null/empty-string behavior per field, the fact that theme may not be cleared, that mood_arc is a wholesale replacement list rather than a merge, and that unspecified fields are left untouched. It also specifies plain-text, single-line formatting.

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?

The description opens with a specific verb and resource ("Rewrite what the song is about") and then defines the object being edited (the brief, its theme, story, mood_arc, setting, tone). It also names rewrite_song_brief as the distinct tool that supersedes this correction, so an agent can separate the two without reading schemas.

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?

It gives an explicit trigger ("When it reads the song wrong ('it's about my father, not a breakup')"), states that only the sent fields change and the rest stay, and points to rewrite_song_brief as the alternative for wholesale replacement. When-to-use, partial-update semantics, and the sibling escape hatch are all 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