Read game output

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

Annotations already establish read-only, non-destructive, closed-world behavior. The description adds something the annotations cannot: the default is incremental/delta output ('only lines you have not seen yet'), which is a non-obvious stateful read semantic an agent must account for when deciding between repeated calls.

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?

Two short sentences, front-loaded with the tool's function followed immediately by its most surprising default. No filler or restatement of the title.

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 correctly indicates what is returned (lines and errors). It stops short of covering edge cases such as behavior when no game is running or whether output is buffered/persisted, but for a simple read tool the coverage is close to sufficient.

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 100%, so tail, onlyNew, errorsOnly, and waitSeconds are fully documented in the schema, and the description's mention of the incremental default simply mirrors onlyNew. Baseline 3 is appropriate since the schema carries the parameter burden.

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 output and errors) and binds it to the originating sibling (run_project), so an agent knows exactly which process this reads from. It is clearly distinguishable from list_projects, get_scene_tree, capture_screenshot and the other siblings.

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 implies the correct usage window by naming run_project as the prerequisite, and states the default retrieval mode. It does not spell out what to do if the game is not running or contrast itself with a full-log alternative, but the context is clear enough to select the tool.

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