central-mcp

Overview Schema Source Related Servers Discussions Admin

project_note

Save what was done, left, and learned for a project, preserving abandoned approaches and intent that git cannot recover. Call it after substantial work so future briefings include the decisions behind the code.

Instructions

Record what was done / what was left / what comes next for a project.

This is the durable memory a return briefing is built from. project_pulse reads the repository and can tell anyone what is true; only you can record what was meant — why an approach was abandoned, what is half finished, what should happen next. None of that is recoverable from git later, so it is lost unless it is written down now.

When to call it — this matters more than the arguments. Call it at the end of any stretch of real work in a registered project, whether or not that work came through central-mcp. A session someone opened directly in the repo is the most common case and the one most likely to be forgotten. Also call it when you learn something that changes the plan, and especially when you abandon an approach: "tried X, it fails because Y" leaves no commit, no diff, no trace at all, and is the single most valuable thing this file can hold.

Do not call it for trivia (a typo fix, a question answered) — an over-full ledger gets skimmed, which is the same as empty.

Arguments: note — free text: what happened, what was left, what was learned. name — registered project name. Omit if passing cwd. cwd — a path inside the project; resolved to whichever project owns it. Use this when you know where you are but not what it is registered as. next_step — one line: what should happen next. A briefing offers this back for confirmation, so write it as an instruction to a future reader, not a note to yourself. source — "agent" when you are recording your own work (default), "user" when you are writing down what the human just told you. Keep these honest: the ledger's whole value is that a reader can tell a first-hand record from a relayed one.

Input Schema

TableJSON Schema

Name	Required	Default
`cwd`	No
`name`	No
`note`	Yes
`source`	No	agent
`next_step`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.20.0Sep 21, 2026

TDQS

A4.6/5.0

Behavior4/5

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

No annotations are provided, so the description carries the full burden. It does the job well: it reveals the side effect (appends to a durable ledger that gets skimmed if over-filled), explains the persistence value (why abandoning an approach matters because it leaves no git trace), and clarifies how next_step is consumed by a briefing. It doesn't claim to be read-only or destructive explicitly, but its behavioral character is clearly communicated. Minor gap: it doesn't disclose whether the note can be edited or deleted later, but that's not critical given no annotations to contradict.

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 description is well-structured with clear sections, bolded lead-ins, and front-loaded purpose. It is longer than the average tool description, but every section earns its place given the tool's unusual depth of meaning (the is-true vs. was-meant distinction, the abandonment case). The 'Arguments' section is compact. One slight deduction: the 'When to call it' paragraph could be tightened, and the parenthetical examples in the abandonment guidance add a small amount of redundancy.

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 tool with 5 parameters, 0% schema coverage, and an output schema present, the description is nearly complete. It explains every parameter's semantics, the when/when-not usage, and the return-value expectation (next_step is offered back for confirmation). It doesn't describe the exact return format beyond that, but an output schema exists to capture that. The only minor gap is the absence of explicit mention of the result of calling this tool (e.g., does it return the saved note?), which the output schema presumably handles.

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 description coverage is 0%, so the description must carry the full weight of parameter documentation — and it does. Every parameter gets meaningful explanation beyond its type: note is what it contains, name vs. cwd are contrasted with a decision rule ('Use this when you know where you are but not what it is registered as'), next_step is specified as an instruction to a future reader (not a note to yourself), and source explains the honesty requirement of the agent/user distinction. The 0% coverage makes a 5 fully justified — the description compensates completely.

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 states a specific verb-resource pair ('Record what was done / what was left / what comes next for a project') and immediately establishes its role as the durable memory for return briefings. It distinguishes itself sharply from sibling project_pulse by drawing the is-true vs. was-meant distinction, which is precisely what separates it from every other project-related tool in the list.

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?

The 'When to call it' section is exemplary: it specifies when to call (end of real work, when the plan changes, especially on abandoning an approach), covers the most-common-but-easily-forgotten case (a session opened directly in the repo), and gives explicit negative guidance (do not call for trivia, because an over-full ledger gets skimmed). This is the strongest usage guidance possible — it names the conditions, not just the context.

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