Ask a collection

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

While annotations provide basic hints, the description adds vital behavioral context that annotations cannot: the latency ('Can take minutes'), the scope of the output (getting answers under each seat/model), and the operational constraint regarding file access.

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 very dense, covering function, constraints, workflow, and operational details in one paragraph. While highly efficient, the density prevents a perfect 5, but it earns 4 for its extremely high information density and front-loading of critical information.

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?

The description is complete by setting a functional goal and describing the full lifecycle of the tool. It manages expectations (time, required input format) and guides the agent toward the next logical step in the workflow (the `verdict` sibling tool).

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?

Since schema coverage is 100%, the baseline is already high. However, the description adds semantic value by instructing the user on required input content ('Give the seats the real text') and clarifying that the `merged` parameter should be omitted when querying 'the collection's own' seats, adding critical usage context to specific fields.

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 clearly states that the tool broadcasts a prompt to every seat within a specified collection. It effectively distinguishes itself by stating, 'Ask a collection, not a favourite model,' immediately clarifying its purpose relative to potential single-model query tools.

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?

The description provides highly specific usage guidelines, including a critical warning: users must provide 'the real text (code, diff, file contents)' because the seats cannot read external files. It also dictates the required post-call workflow: 'Verify every claim... send a verdict per seat you judged.'

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