agy_run

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

Annotations already flag openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds real value beyond them: cost may be incurred, CLI tools become available to the model, and there is no automatic retry. It stops short of saying what a failure or success looks like.

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?

A single dense sentence with the action first and the risk constraints trailing; the 'No retries' fragment is deliberate emphasis rather than noise. Nothing could be cut without losing signal.

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 one-parameter, non-idempotent, cost-incurring invocation with no output schema, the description should indicate what comes back (model stdout? status/exit code?) and what happens when the run fails. Those gaps keep it at minimum-viable rather than complete.

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?

The single 'prompt' parameter has 0% schema description coverage, so the description is the only source of meaning – yet it only implies that one prompt string is supplied. Nothing about size limits, formatting, or what 'authorized' means for the prompt content.

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?

States a specific verb and resource: sends one prompt to the configured CLI model. The adjective 'one' plus 'CLI model' distinguishes it from the discussion/council siblings that orchestrate multi-turn exchanges, though the description never names those siblings explicitly.

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?

There is no statement of when to pick agy_run versus agy_discussion_turn or agy_council_round, all of which plausibly also submit prompts. 'No retries' hints at fire-and-forget semantics but is not framed as usage guidance, and no prerequisites (config, authorization) are described.

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