script

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

Exposes significant behavioral traits beyond the false-boolean annotations: the sandbox is only protection against accidents, not against untrusted input; write_script/edit_script enter the same threat surface as execute_gdscript via pre-write scanning; the dangerous-pattern list is deliberately hidden to prevent sandbox-boundary probing. This gives agents the true security model and the reason for information withholding. Misses some specific write-behavior details (output/return behavior, confirmation flow), so not a 5.

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 and front-loaded: the action list appears in the first few words, and every sentence carries meaningful security or usage content. It loses a point for being one long flowing block — the two important caveats are embedded mid-sentence, and explicit line breaks or bullets would improve agent scanning.

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?

For a tool with 21 parameters, 7 actions, nested objects with no output schema, the description supplies the high-value operational context (security threat model, sandbox boundaries, execute best practices). The remaining gaps are noticeable but not blocking: no statement of return/output behavior, and no mention of whether destructive actions need additional confirmation or iterate (e.g., project_replace write visibility).

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 every parameter is already documented in the input schema. The description adds essentially nothing beyond the schema: it references edit_script's line-number/search_and_replace and project_replace's bulk replacement, which the schema already captures in parameter descriptions. Baseline 3 is appropriate.

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?

Description gives 'script operations' as the domain and enumerates all seven actions with their verb categories: read/write (read_script, write_script), edit (edit_script), execute (execute_gdscript), test (generate_test, create_test_scene), bulk replace (project_replace). This clearly distinguishes the internal actions, though it stays a dispatcher-level description and does not differentiate from sibling tools like 'cpp' explicitly.

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?

Provides explicit routing guidance for every action family, and goes further: it says when NOT to trust execute_gdscript (untrusted input), when to use ALLOW_EXECUTE_GDSCRIPT=false, and recommends a step-by-step 'execute-verify-iterate' pattern for complex logic. Lacks explicit comparison to sibling tools, so it earns a 4 rather than a 5.

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