game_logs

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

Annotations declare readOnlyHint=true and destructiveHint=false. The description adds that it is real-time and no file logging, and discloses that setting clear=true empties the buffer after reading, which is a behavioral side effect beyond annotations.

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, with three to four sentences that front-load the purpose and parameter details without unnecessary 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?

The description covers the tool's purpose and parameter semantics, but lacks details about output format (e.g., plain text or structured) and does not describe the exact structure of errors or return values. Given no output schema, this is a moderate gap.

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 only 25%, but the description adds detailed meanings: level options with their effects, limit default of 100, filter as substring, and clear empties buffer. This compensates well for the sparse schema.

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 it reads real-time game logs from the runtime channel, covering errors with stack traces, warnings, and print statements. It explicitly contrasts with the sibling tool logs_read, which cannot reliably cover this real-time output.

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 explains that this tool is for real-time debugging ('play->see-error->fix signal') and contrasts it with logs_read for file-based logs. It provides parameter guidance (level, limit, filter, clear) but does not explicitly state when not to use it.

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