Skip to main content
Glama

Arroway

Take back your own pending proposal

arroway_withdraw
Idempotent

Take back a pending PROPOSAL that turned out to be wrong — typically because the human corrected you after it was written. Pending proposals only; a memory the human already sanctioned is theirs, and changing it goes through them. A proposal written by SOMEONE ELSE's AI can also be taken back — the archive belongs to the project — but Arroway stops first, names who wrote it and what would leave their review queue, and the next call with other_author_confirmed=true finishes it. This is not deletion: the proposal is kept, marked as withdrawn, with your reason. If the corrected version is durable, write it with arroway_remember too — leaving the right answer only in your own notes is how Arroway ends up holding the wrong one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
whyYesWhat made it wrong — usually what the human said. This is the part worth keeping.
memoryYes#handle of the proposal, from a read
projectYes
other_author_confirmedNoOnly after Arroway told you the proposal was written by someone else's AI: set true to go ahead. Never set it blindly on a first call — the point of the stop is that the person hears whose work is leaving the queue before it leaves.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description goes well beyond the annotations: it discloses the non-destructive nature ('kept, marked as withdrawn'), the two-call confirmation flow for another author's proposal, and the consequence of leaving corrections only in personal notes. This is consistent with destructiveHint=false and idempotentHint=true, with no contradiction.

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 long but every sentence carries essential decision-relevant information: scope, exclusions, cross-author behavior, non-deletion semantics, and the follow-up tool. It is front-loaded with the core purpose and then layers edge cases in a readable order with no filler.

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?

For a tool with four parameters, no output schema, and a subtle non-destructive withdrawal flow, the description covers all important context: when withdrawal is allowed, how the other-author stop works, what happens to the proposal, and what to do with the corrected version. An agent has enough to invoke it correctly.

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 75%, so the schema already documents why, memory, and other_author_confirmed in detail. The description reinforces the flow around other_author_confirmed but adds little parameter-level meaning beyond what the schema provides, so baseline 3 is appropriate.

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: take back a pending PROPOSAL. It sharply distinguishes this from deletion ('This is not deletion: the proposal is kept, marked as withdrawn') and from other tools like arroway_remember, so an agent can tell exactly what arroway_withdraw is for.

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?

It states when to use it ('pending PROPOSAL that turned out to be wrong'), when not to use it ('a memory the human already sanctioned is theirs, and changing it goes through them'), and what to do instead for durable corrections ('write it with arroway_remember too'). This gives an agent both positive and negative selection criteria.

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.