get_debug_output

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

Goes well past the readOnlyHint=true annotation: it discloses that captured logs survive process exit and crashes, that the session clears itself on exit, that logs are retained until stop_project, and that attached mode yields empty arrays with running=null. These are exactly the lifecycle and edge-case behaviors an agent needs and cannot get from annotations or schema.

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-loads the purpose, then usage trigger, then lifecycle caveats, then return shape in tight successive sentences. Despite being relatively long, every clause carries distinct operational information - no filler or repetition.

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?

Covers prerequisite tooling, retention semantics, post-crash retrieval, attached-mode behavior, and return-field semantics. Even though an output schema exists (making the return-value prose partly redundant), the description leaves no gap an agent needs filled before calling 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?

With one parameter at 100% schema coverage, the baseline is 3. The description restates the default of 200 and adds that it applies per-array ('last limit lines each'), which mildly enriches the schema's 'from end of output' wording, but it does not introduce new meaning beyond the 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?

States a specific verb and resource ('Get captured stdout/stderr from a spawned Godot project') and immediately scopes it to runtime diagnostics. It is clearly distinguishable from siblings like run_project, stop_project, and the editor/profiling tools.

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?

Explicitly says when to reach for it ('whenever runtime tools fail unexpectedly - script errors, missing nodes, and crash backtraces all surface here') and names a hard prerequisite and its alternative ('Requires run_project (not attach_project; attached mode does not capture output)'). Both the trigger condition and the exclusion are stated, leaving nothing to inference.

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