AUTH: atomically transfer your one deterministic settlement voice to an already-filed exact-input correction. Both rows remain public.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | No | ||
| attempt_id | Yes | ||
| successor_attempt_id | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does provide some useful disclosures: the operation is atomic and leaves both rows public. However, it does not explain the full side effects, such as whether the original attempt loses the settlement voice, whether the action can be reversed, or what the AUTH marker actually requires.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loads the auth and atomicity cues before the core action. The phrasing is dense but every portion contributes; a fifth point is withheld because the AUTH marker and domain jargon are cryptic without supporting context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a state-changing tool with no annotations, no output schema, and no per-parameter documentation, so the one-sentence description is insufficient for confident invocation. Missing context includes what a deterministic settlement voice is, what happens to the original row's voice, and the operational prerequisites or failure modes.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema descriptions are absent, but the description partially clarifies the parameters: successor_attempt_id is the already-filed exact-input correction and attempt_id is the prior row, with both rows remaining public. The optional reason parameter still receives no semantic explanation beyond its self-evident name and length constraint.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description identifies a specific action: transfer the caller's deterministic settlement voice to an already-filed exact-input correction atomically. It also notes a useful state outcome: both rows remain public. It does not, however, differentiate itself from sibling tools like replace_vote or withdraw_vote, so it stops short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given about when to use this tool versus alternatives such as replace_vote, vote, or abort_attempt, nor are exclusions stated. The only contextual clue is the prerequisite that the correction already be filed, which is too weak for an agent to make routing decisions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have unique resource nouns, but several clusters overlap in purpose: get_progression, get_decisions, get_queue, and get_dispute_triage all describe next-action/status views, and the flagship/runbook/register families require careful reading to distinguish. The detailed descriptions help an agent choose correctly, but boundaries are not always obvious.
There is a strong get_/list_ convention for reads and imperative verbs for writes, making the set largely predictable. Minor deviations such as whoami, how_to_participate, my_suggestions, propose, and second break the pattern slightly but do not make names chaotic.
47 tools is far beyond the well-scoped band and will overwhelm an agent's tool-selection surface. Even if the domain is complex, many read-only projections could be consolidated into fewer parameterized tools.
The core lifecycle is well covered: propose, second, measure, vote, withdraw/replace, retract, and attempt management are all present, with extensive read support. Minor gaps exist around explicit recertify/dispute-settlement write tools and there is no direct edit operation, but the existing supersession/correction mechanisms largely cover those needs.
