Delete a custom script

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the agent knows this is an irreversible-feeling mutation. The description adds a genuine behavioral fact the annotations do not carry: the required permission is manage_scripts. It does not, however, state that deletion is permanent, whether confirmation or preview is honored, or what happens to scripts referenced by automations.

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?

Only three short sentences, but the second ('Deletes an existing custom script specified by its ID') is a near-verbatim restatement of the first and earns nothing. The useful permission note is buried last rather than front-loaded alongside the warning about permanence.

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?

An output schema and rich annotations mean the description need not explain return values, and all three params are covered. However, for a destructive, open-world deletion, the description should at minimum flag irreversibility and the confirm/'YES' safeguard rather than leaving safety entirely implicit in the schema.

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%, with script_id, dry_run and confirm all documented in the schema itself. The description only restates 'specified by its ID', adding no syntax, format, or guidance on the dry_run/preview default. Baseline 3 is appropriate when the schema does the work.

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: 'Delete a custom script', with scope narrowed to a script identified by ID. It is clear what the tool does, though it does not differentiate itself from the many other delete siblings (delete_package, delete_setting, delete_automation), which all read similarly.

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?

No indication of when to delete vs. when to use update_script, list_scripts, or get_script to verify first, and no mention of prerequisites beyond 'Perm: manage_scripts'. The existence of a dry_run/confirm safety flow is left entirely to the schema with no narrative guidance.

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