run_until_text

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

With no annotations, the description fully discloses key behaviors: substring matching on the entire decoded screen (not row-anchored), early return on match, timeout with `found=False`, and the return object keys. It also explains the performance implications of chunk size, which is valuable context beyond the schema.

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 concise (~90 words) and front-loaded with the core purpose. Every sentence adds value: matching semantics, alternative usage, early return, timeout behavior, chunk trade-off, and return format. No redundancy or filler.

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?

Despite having no annotations and 0% schema coverage, the description provides a complete operational picture. It covers behavior, termination conditions, return values, and gives actionable guidance. The presence of an output schema is supplemented by the explicit specification of return keys. The tool's complexity is well addressed.

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 description coverage is 0%, but the description compensates by explaining the meaning of `needle` (the text to find), `max_cycles` (timeout), and `chunk_cycles` (chunk size). The `session_id` parameter is not explicitly described, but it is a common identifier likely inferred from context. This is strong compensation but not perfect coverage of all parameters.

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 the tool's function: 'Run in chunks until `needle` appears anywhere in the MODE 7 screen.' It uses a specific verb (run), a specific resource (MODE 7 screen), and a condition. It also distinguishes itself from sibling tool `run_until_prompt` by explaining the difference in matching semantics.

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?

Explicit guidance is provided: 'Use `run_until_prompt` when the marker must sit at the start of a row.' This directly addresses when to use an alternative. The description also explains the trade-off of chunk size, helping the agent choose appropriate values.

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