remove_init_script

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and closed-world scope, so the safety profile is largely covered. The description adds genuinely useful behavior beyond that: the removal is not retroactive ('pages already loaded keep what it did') and it errors on ids the session doesn't hold. It still doesn't say whether the script is skipped on subsequent navigations versus current page state.

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 compact clauses with no filler; the core action, the scope caveat, and the error behavior are all front-loaded.

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 two-parameter mutation tool with full annotations and an output schema, the description covers purpose, scope of effect, and error behavior. The only slight ambiguity is whether get_emulation lists init-script ids or emulation settings, and what exactly removal affects going forward.

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 both parameters are already documented in the schema, including that id comes from add_init_script and sessionId from open_browser_session. The description only adds a hint that ids can be enumerated via get_emulation, which is marginal value over 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 ('Stop running an init script') and anchors it to the sibling that creates such scripts (add_init_script), so an agent can distinguish it from add_init_script or get_emulation without opening a 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?

Clear context for use: undo a script registered via add_init_script. It also gives a fallback discovery path ('get_emulation lists them') and a failure condition for bad ids, though it never explicitly names a 'when not to use' case.

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