script_manage

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

With no annotations, the description carries the full burden. It discloses that `detach` is 'Undoable' and removes the currently attached script, and specifies the return values for `read` (full source, line count, file size) and `find_symbols` (class_name, extends, functions, signals, @export vars). It does not cover permissions, error handling, or session requirements, but the key side effect (detach) is disclosed.

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 compact and front-loaded: a one-sentence summary, then a resource form note, a bulleted op list, and a canonical call shape. No sentence is wasted, and it uses markup for scannability.

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 multi-op tool with three operations and an output schema, the description covers the resource form, each op's purpose/return, and the invocation format. It omits edge cases like error behavior and when `session_id` is mandated, but the presence of an output schema fills some return-value gaps. Overall, it is sufficiently complete for an agent to invoke correctly in typical scenarios.

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 0% for parameter explanations, but the description enriches each op with its expected argument (e.g., `read(path)`, `detach(path)`, `find_symbols(path)`) and shows the canonical call shape. This compensates for the opaque `params` object (additionalProperties: true) but leaves `session_id` unexplained, though the schema provides a default.

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 opening line explicitly states 'Script (.gd) reading, detachment, and outline,' naming the resource and three distinct operations (read, detach, find_symbols). This clearly distinguishes it from sibling script tools like script_create, script_patch, and script_attach.

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 provides clear operational scope by enumerating the three ops and notes a preference for the `godot://script/{path}` resource form for active-session reads. However, it does not explicitly contrast with sibling tools or state when not to use each op, though the op names and behavior make usage contexts self-evident.

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