agy

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

No annotations are present, so the description bears the burden. It discloses synchronous execution and return content, and mentions parameters like allow_write and sandbox that hint at side-effect control, but it does not specify permissions, side effects, or operational risks.

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 two sentences, efficiently delivering the core action, return type, and parameter compatibility. No filler or redundancy; information is front-loaded.

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?

With 15 parameters, 0% schema coverage, and no annotations, the description is too thin. It relies heavily on familiarity with the legacy gemini tool and does not explain modes, enums, or the output structure beyond 'assistant text + metadata'.

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%, so the description must compensate. It lists parameter groups ('same PROMPT / cd / ...' and 'new mode / timeout / ...') but does not explain the meaning of individual parameters or enum values, leaving the agent without sufficient semantics.

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 explicitly states 'Run agy --print synchronously and return the assistant text + metadata', providing a specific verb, resource, and output. It distinguishes this from sibling tools like agy_start and agy_continue by positioning it as the primary execution tool.

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 offers clear context by calling itself a 'drop-in for the legacy gemini tool', indicating when it should be used (when you would use gemini). However, it does not explicitly contrast with siblings or provide exclusions, but the inference is straightforward from the names.

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