Create a multi-model council task that collects sealed initial judgments from GPT, Gemini, and Claude and assigns separate 1–8 attempt budgets without making model calls.
Create a GPT/Gemini/Claude task with sealed initial judgments and separate 1..8 AGY attempt budgets. No model call.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | Yes | ||
| facts | No | ||
| max_turns_per_model | No |
Changes observed during successful MCP inspections.
v0.5.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a non-read-only, non-destructive, closed-world creation operation. The description adds that it makes no model call and involves sealed judgments, but it omits persistence, side effects, and what creation enables, so it only partially supplements annotations.
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?
One front-loaded sentence with no filler, but the density of unexplained acronyms makes it more under-specified than efficient. Structure is acceptable for a short description.
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?
For a 3-parameter creation tool with no output schema, the description is too thin: it does not explain return behavior, how facts are used, what sealed judgments mean operationally, or how budgets are applied. Annotations cover safety only, leaving an agent to infer the workflow.
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 coverage is 0% and the description does not define goal, facts, or max_turns_per_model. The phrase '1..8 AGY attempt budgets' loosely gestures at budget behavior but does not map to the max_turns_per_model parameter (default 2) or explain required goal/facts.
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 states the verb create and a resource task, and notes 'No model call', but 'GPT/Gemini/Claude task', 'sealed initial judgments', and 'AGY attempt budgets' are undefined jargon. It does not differentiate from agy_discussion_create or agy_run, so the intended council object is only inferable from the tool name.
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 when-to-use guidance, prerequisites, or alternatives are given. 'No model call' hints that this is a setup-only tool, but the description never says to use it before agy_council_round/reveal or instead of agy_run.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.