Skip to main content
Glama

Narrate a live set (persisted decision log)

narrate_set

Record timestamped narration lines during a live VJ or show set to create a persistent set log. Append notes with optional sections and cues, or recall previous entries.

Instructions

Persist the running narration of a live VJ/show set so decisions can be recalled afterwards. mode='append' adds a timestamped line (with optional section + cue) to a markdown session log (default ~/.tdmcp/narration-.md); mode='recall' reads the log back (last tail lines). Pair with the auto_vj_director prompt: instead of narrating only in chat, call narrate_set on each major move so the set leaves a diary/setlist trail. Writes a local file (not read-only). Delta vs log_performance, which writes a one-shot network snapshot rather than an append-only decision log.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cueNoOptional cue name being fired/recalled, for cross-reference.
lineNoThe narration line to record (required for mode='append'), e.g. "holding through the build → cue 'drop' on the next bar".
modeNoappend: add a narration line to the running set log. recall: read back the log lines.append
tailNoFor mode='recall': return at most the last N narration lines.
sectionNoOptional song section/phase this line belongs to, e.g. 'intro', 'drop', 'breakdown'.
log_pathNoExplicit path to the narration log file, overriding set_name. Honors TDMCP_NARRATION_PATH otherwise.
set_nameNoSession name; picks the log file ~/.tdmcp/narration-<set_name>.md. Defaults to today's date.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYes
countYesTotal narration lines in the log.
entriesNoParsed narration entries (mode='recall').
appendedNoThe entry that was appended (mode='append').
log_pathYesAbsolute path of the narration log file.
Behavior5/5

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

Description discloses that the tool writes a local file (not read-only) and is append-only, complementing the annotations (readOnlyHint=false, destructiveHint=false). It also mentions timestamping, markdown format, and default file path, offering thorough behavioral context beyond structured data.

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?

The description is concise, with each sentence contributing meaningful information. It is front-loaded with purpose and efficiently covers usage, modes, file details, and sibling differentiation.

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?

Given the tool's complexity (two modes, seven parameters, file writing), the description covers all essential aspects: mode behavior, file path, defaults, pairing suggestion, and comparison to a sibling. With full schema coverage and an output schema present, no critical gaps remain.

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 100%, so baseline is 3. The description adds value by explaining how parameters relate to modes (e.g., line required for append, tail for recall) and provides file path defaults and optional fields (section, cue), enhancing semantic understanding.

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 clearly states the tool persists running narration of a VJ/show set for later recall, with specific modes (append/recall). It distinguishes itself from the sibling tool log_performance, which writes a one-shot snapshot instead of an append-only log.

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?

Describes when to use: call on each major move during a set to leave a diary/setlist trail. Explicitly contrasts with log_performance as an alternative, providing clear guidance on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pantani/tdmcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server