debug_output

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds substantial behavioral context beyond them: output and errors are drained on each call so successive calls return only new data, the return shape (lines, errors, their counts), and the ZERO-BASED line convention. The drain semantics are exactly the kind of non-obvious behavior an agent needs to avoid misreading results.

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?

Front-loaded with the core action and densely packed with useful detail; nearly every clause earns its place. It runs slightly long and mixes return-shape and behavior in a busy sequence, but stays on topic with no 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?

With no output schema, the description carries the burden of explaining return values ('Returns: lines, errors, and their counts') and it does so, along with drain semantics and line-numbering convention. For a two-optional-parameter read tool, nothing an agent needs to call it correctly is missing.

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 100%, so both parameters (wait, clear) are already fully documented in the schema, establishing the baseline of 3. The description's drain-on-call note gives indirect meaning to 'clear' but does not add syntax or defaults beyond what the schema provides.

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?

States a specific verb and resource ('Read what a game started with debug_run produced') scoped to print() output, stdout/stderr, and structured errors. It explicitly differentiates from the language server tools that report compilation rather than runtime output, so an agent can tell it apart from siblings like debug_status and debug_stack_trace.

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?

Gives clear when-to-use context ('THIS IS THE ONLY WAY to see what the game actually did') and contrasts with the language server's compile-only reporting. It does not name the most likely alternative sibling (runtime_output) or state when-not to use it, keeping it short of a full 5.

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