scene_remove_client

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

Beyond the annotations (destructiveHint=true, readOnly=false), the description discloses concrete behavioral facts: it writes a new .gil into the workspace, and it refuses removal when a script is still held by controls or a template is named by a grid/reference—returning the holder names. This is exactly the extra context annotations can't convey.

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 core action and constraints, with each sentence adding real value (alternatives, refusal rules, output artifact). It is dense with parenthetical nesting, which slightly hurts scannability, but no sentence is wasted.

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 destructive, non-output-schema removal tool it covers what an agent needs: what gets removed, the one-of-three constraint, dependency refusals, and that a new .gil is written. The only gap is the unexplained mapPath/outputName parameters, which prevents a top score.

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%, so the description must carry parameter meaning. It clarifies that ui is the name from scene_add_client_ui, that template is a template of client controls, and that script is a client script—useful semantics for three params—but mapPath and outputName are left entirely unexplained, so compensation is only partial.

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 (take out/remove) applied to three concrete resources—client interface (ui), template of client controls, and client script—and explicitly scopes it as 'one of the three in a call.' It also names the sibling tools that manipulate the same resources (scene_get_client_ui, scene_add_client_ui, scene_set_client_script), so an agent can distinguish it without opening any schema.

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 describes when NOT to use it ('To change an interface or a template that is there, this is not needed') and routes the agent to the correct alternatives (get+add with replace:true for UI/template, scene_set_client_script for scripts). The one-of-three constraint and dependency-refusal condition are stated directly.

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