Skip to main content
Glama

Arroway

Log what a task left behind

arroway_log

Append the durable residue of a COMPLETED task to your daily log in Arroway: what someone arriving later would need in order not to redo it. You judge the length — say what carries, cut what does not. Dated state (numbers, statuses) belongs here; it ages out naturally. Team-visible. ALWAYS write the authored essence too: it is the one line the normal project read serves. An older, frozen catalog that truly has no essence field may still write the body; Arroway marks that entry as pending a reviewable essence proposal, never as if one had been authored. One thing that belongs here and nowhere else: if the person corrected you for insisting on something already decided, say so in the entry, so the memory that keeps being re-litigated can be flagged. AND CLOSE WHAT THIS WORK REALIZED: every memory in the read carries 'dies when: …'. If this task made that condition true — the idea was built, the intention was carried out, the dated status was replaced — name it in fulfills and Arroway retires it in the same act, with this entry as the reason; the human never has to archive the obvious by hand. Only decisions, facts and references can be fulfilled, and only ones this connection actually received in a read.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicNoOptional free tag (e.g. 'marketing')
sourceNoOptional pointer to a living source (URL, doc, CRM id)
contentYesThe full durable residue: what was decided, found or changed, and what it cost. It remains recoverable by handle.
essenceNoOne authored line with the operative result. This is what the normal project read serves; never copy the opening of the body.
projectYesProject slug. If it did not come from the person or from a read in this session, it is a guess: check it against the roster that opens arroway_catch_up before writing, because material from one circle must never land in another.
fulfillsNoARROW-290. The memories this completed work REALIZED — their 'dies when' condition is now true because of what you did (a routine that an idea asked for is running; a planned move was made; a dated status has been replaced by what this entry records). Each one is retired in the same act as this log, with your 'how' as the reason on its archived line, reversible from the panel. Guards: only decision/fact/reference (a rule is never 'fulfilled'), and only memories this connection received in full in a read — if any item fails, the whole call is refused and nothing is written. Never list a memory because it merely looks old or unused: that is not evidence.
backfilledNoTrue when the entry describes something that happened BEFORE Arroway existed (history you are bringing in), not today's work.
keep_wholeNoSet true only after you considered cutting an indivisible oversized residue. Arroway records this exception for calibration; it never truncates your text automatically.
operationalNoSet true when this is the record of HOW THE WORK WENT — what failed, what you measured, what you corrected about your own earlier reading. It is kept in full for catching up at the start of a session, and stays OUT of the task-scoped read, so a long account never pushes a teammate's residue out of their block. Leave it out (the default) for what the team needs to know HAPPENED: that is what reaches other people while they work. This is a record of work, never a transcript of the conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

The description goes well beyond the annotations: it discloses that fulfilled memories are retired in the same act, that the retirement is reversible 'from the panel', that entries without an essence are marked as pending a reviewable proposal, and that the call is refused if any fulfills item fails. These are meaningful side-effect behaviors. No contradiction with annotations exists; readOnlyHint=false and destructiveHint=false are consistent with an append-plus-retire operation that is reversible.

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 dense and long, but almost every sentence adds operational guidance. It is front-loaded with the primary purpose and then layers correctness rules. Some repetition and capitalization make it harder to scan, but the length is largely justified given the tool's complexity and the important side-effect behavior that must not be missed.

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 9-parameter write tool with no output schema and partially informative annotations, the description is thorough. It explains the write obligation, the essence rule, the fulfills/retirement behavior, and the exception for frozen catalogs. The remaining gaps — such as explicit guidance for operational, backfilled, topic, and source — are adequately covered in the input schema's own descriptions, so the description is not incomplete enough to cause misinvocation.

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 the baseline is 3, but the description adds substantial guidance beyond the schema. It explains what should go into content ('say what carries, cut what does not'), that essence is mandatory for normal entries, which dated states belong in the log, and what 'fulfills' means in terms of killing conditions. This materially improves an agent's ability to populate the most nuanced fields.

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: 'Append the durable residue of a COMPLETED task to your daily log in Arroway'. It clarifies the tool is for durable, team-visible task residue and explicitly distinguishes it from other log/read tools by emphasizing this is what remains after completion. This is specific enough to differentiate it from sibling tools like arroway_remember or arroway_pass.

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?

The description gives clear context: use it for completed task residue, not for conversation transcripts or open work. It also says what belongs here ('Dated state', 'the person corrected you...') and what does not, and explains the fulfills mechanism. It does not explicitly name alternative tools or give explicit 'when not to use' exclusions, so it stops short of a 5.

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.