game_logs

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

The description claims read-only behavior but also discloses that clear=true empties the buffer after reading. This is a side effect that contradicts the readOnlyHint annotation. Although the description is transparent about the side effect, the annotation is misleading, and the inconsistency warrants a low score.

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 dense but well-organized: a lead sentence states the tool's core function, followed by the primary use case, then a compact parameter reference. Every sentence adds value, and the structure makes it easy to scan. No wasted words.

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?

Given four parameters, no output schema, and the need to differentiate from a sibling tool, the description is complete. It covers real-time behavior, content types, defaults, clear side effect, and alternative tool. The agent has all necessary information to invoke it correctly.

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 description thoroughly explains all four parameters beyond the schema. It defines legal values for level (error, warning, all), default for limit (100), filter as substring, and clear's side effect. This compensates for the low schema coverage (25%) and adds meaning to each parameter.

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 reads the running game's captured output from the runtime channel, specifying the types of output (errors with stack traces, push_error/push_warning, print). It explicitly distinguishes itself from logs_read (file-based), making its purpose unambiguous.

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 explicitly tells when to use this tool: for real-time runtime output that logs_read can't reliably cover, framing it as the 'play->see-error->fix signal'. It also names the alternative (logs_read) and describes parameter usage for level, limit, filter, and clear, which guides selection and invocation.

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