Jean by Melad Labs

record_experiment

Write what just happened into your lab notebook: a new entry, or more text appended to one you name. The body is markdown and its @plasmid / !action / &gel references are extracted as you write, so an entry made by a run is cross-linked exactly like one you typed — and carries the automated tag, so you can always tell which is which. Use it to end a pipeline with a record of itself instead of a reminder to write one.

Input Schema

Name	Required	Description
`tags`	No	tags to file it under, beyond the `automated` tag every entry written here carries.
`title`	No	the entry title. A new entry needs one. On an append, giving a title RENAMES the experiment, so leave it out to keep the name it has.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`body_md`	Yes	the entry body, markdown. `@plasmid-name`, `!action-id` and `&gel-id` references in it are extracted into the entry's cross-reference lists, which is what makes a notebook searchable by construct.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`entry_id`	No	append to this entry instead of creating one — the id `list_experiments` returns. A pipeline that runs twice should append to its own entry rather than leaving two.
`collection`	No	file it in this collection, creating the collection if it does not exist — the notebook's own grouping, the same one the panel lists.

Output Schema

Name	Required	Description
`tags`	Yes	the tags as stored, including `automated` — the engine caps and cleans these, so read them back rather than assuming
`title`	Yes	the title it now carries
`created`	Yes	true for a new entry, false when text was appended to an existing one
`entry_id`	Yes	the entry written — pass it back to append to this same experiment next time
`bodyChars`	Yes	the stored body length. The engine caps a body at 1,000,000 bytes, so a long append can be shorter here than what was sent — read it rather than assuming the write was whole
`crossRefs`	Yes	the @plasmid / !action / &gel references the engine extracted from the body — empty lists are a real answer and mean the body named no construct, which is worth noticing in an entry about one
`collection`	Yes	the collection it is filed in, or an empty string when it is filed in none
`unresolved`	Yes	`{ references, citations }`: every `@` / `!` / `&` reference in the stored body that names nothing in this workspace, as written, and every citation key that is not a DOI, PMID or PMCID. Empty lists mean every reference resolves; fix and append when they are not. Null when the write ran without the check (a blocking workflow run)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 23, 2026

addedOutput schema / properties / unresolved

Added value: +{
+  "description": "`{ references, citations }`: every `@` / `!` / `&` reference in the stored body that names nothing in this workspace, as written, and every citation key that is not a DOI, PMID or PMCID. Empty lists mean every reference resolves; fix and append when they are not. Null when the write ran without the check (a blocking workflow run)"
+}

changedOutput schema / required

Previous value: -[
-  "entry_id",
-  "created",
-  "title",
-  "tags",
-  "crossRefs",
-  "collection",
-  "bodyChars"
-]New value: +[
+  "entry_id",
+  "created",
+  "title",
+  "tags",
+  "crossRefs",
+  "collection",
+  "unresolved",
+  "bodyChars"
+]

First observedOct 20, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Beyond the annotations (which only say it is a non-destructive write), the description discloses the important side effects: references in the body are auto-extracted into cross-reference lists, every entry written here carries an `automated` tag so provenance is distinguishable, and appends share the entry rather than creating duplicates. That is exactly the behavioral context an agent cannot infer from readOnlyHint/destructiveHint.

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?

Three sentences, front-loaded with the action and the two modes, then the consequence (auto cross-linking, `automated` tag), then the motivating use case. No filler and nothing buried.

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?

With annotations covering safety and an output schema covering returns, the description supplies the remaining agent-relevant facts: write semantics, append behavior, tagging, and reference extraction. Nothing needed to call it correctly is missing.

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 coverage is 100% and the schema already documents body_md reference extraction, title-rename-on-append, and the `automated` tag in `tags`. The description's note about markdown bodies and @plasmid/!action/&gel extraction largely restates the schema, so it earns the baseline rather than more.

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 — 'write ... into your lab notebook' — and immediately disambiguates the two modes (a new entry, or appended text to a named one). An agent can distinguish this from list_experiments or notebook_cross_refs without opening any schema.

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?

Gives a clear intended use case ('end a pipeline with a record of itself instead of a reminder to write one') and the append-not-duplicate rule appears in the schema. It stops short of naming siblings to prefer for reading or searching the notebook, so there is context but no explicit exclusions.

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

All Jean by Melad Labs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?