game_logs

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

Despite readOnlyHint=true, the description transparently discloses a side effect: 'clear=true empties the buffer after reading.' It also explains the real-time/no-file-logging behavior, level filtering effects, and default limits, going well beyond what the annotations convey.

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 every clause earns its place: purpose, distinguishing comparison, and all parameter semantics are packed into a compact paragraph. It is front-loaded with the most important fact and does not waste 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?

With no output schema and sparse parameter schemas, the description carries a heavy burden and meets it. It explains what output is captured, how to filter levels, how to limit and filter results, and how to clear the buffer. Nothing essential is missing for an agent to call the tool 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?

Schema coverage is only 25%, with only the level parameter documented. The description compensates fully: level behavior is explained (error default, warning adds warnings, all adds print/stderr), limit default is given as 100, filter is described as substring, and clear's buffer-emptying effect is stated.

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 opens with a specific verb and resource: 'Read the RUNNING game's captured output off the runtime channel.' It enumerates exactly what is captured (script errors with stack traces, push_error/push_warning, print) and explicitly distinguishes itself from the file-based sibling logs_read.

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 directly states when this tool is the right choice: it is 'the play->see-error->fix signal' and covers the 'blind spot logs_read (file-based) can't reliably cover.' This gives the agent a clear comparative decision rule without needing to inspect either tool's implementation.

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