tdmcp

Load or initialise the persistent session profile

load_session_profile

Loads a session profile to return unified artist preferences and past work, starting each session with context without running multiple tools. Creates a default if missing.

Instructions

Reads ~/.tdmcp/session-profile.json (or a custom path) and returns a unified JSON snapshot that an agent should load at the start of every session. The profile caches the most recent outputs of style_memory, recall_similar_work, learn_conventions, and learn_from_my_corpus so the agent has the artist's preferences and past work at hand without running all four tools every time. If no file exists, a default skeleton is created and returned. Pass reset=true to overwrite with fresh defaults. The profile_path field in the returned object is always the resolved path that was read or written.

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": "load_session_profile"
  }
}

Input Schema

Name	Required	Description	Default
`reset`	No	If true, overwrite the existing profile with the built-in defaults and return them.
`profile_path`	No	Absolute path to the session-profile JSON file. Defaults to ~/.tdmcp/session-profile.json.

Output Schema

Name	Required	Description
`notes`	Yes	Human-readable notes about what was loaded or defaulted.
`reset`	Yes	True when reset=true was requested.
`created`	Yes	True when the profile was created fresh (no prior file).
`loaded_at`	Yes	ISO-8601 timestamp of this read.
`conventions`	No	Snapshot from learn_conventions (Memory/conventions.md) if previously captured.
`recent_work`	No	Top hits from recall_similar_work if previously captured.
`corpus_style`	No	Snapshot from learn_from_my_corpus (Memory/corpus_style.md) if previously captured.
`profile_path`	Yes	Absolute path of the profile file read or written.
`style_memory`	No	Snapshot from style_memory (Memory/style.md) if previously captured.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.13.1Aug 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false, but the description adds important behavior: it creates a default skeleton if no file exists, overwrites when reset=true, and always returns the resolved path. This clarifies that the tool mutates the filesystem only in controlled ways and adds context about the file path behavior beyond annotations.

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 four sentences long, front-loaded with the main action, then adds purpose, edge-case behavior, and a return-field note. Every sentence earns its place without redundant or vague wording.

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?

Given the tool has an output schema and only two optional parameters, the description is quite complete: it covers default path, custom path, default creation, reset behavior, and the resolved path in the return. Minor gaps such as error handling for corrupted files are not critical for this simple tool, so a 4 is appropriate.

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 description coverage is 100%, so the baseline is 3. The description's mention of 'custom path' and reset=true essentially repeats what the schema parameters already document. It does not add substantive new meaning for the parameters beyond the schema definitions.

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 reads ~/.tdmcp/session-profile.json and returns a unified JSON snapshot, with specifics about creating a default if absent. It also distinguishes itself from sibling tools by explaining it caches outputs of four other tools, so the agent can load a session profile without running them.

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?

Explicitly instructs the agent to load it 'at the start of every session' and frames it as a substitute for running style_memory, recall_similar_work, learn_conventions, and learn_from_my_corpus every time. This provides clear when-to-use guidance and a direct comparison to alternatives.

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

Deploy Server