sieve_delete_script

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

With no annotations provided, the description carries the full burden and does so well: it discloses the destructive outcome, a server-side guard that blocks the active script, a side effect (a local backup is written first), and the return value (backup file name). That is exactly the context an agent needs before committing an irreversible-looking mutation.

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?

Four short sentences, each carrying a distinct fact (what it does, what it refuses, what side effect it produces, when to invoke). Front-loaded with the action and no filler.

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 3-parameter mutation tool with no annotations and no output schema, the description covers action, guard, side effect, return value, and invocation policy. The only gap is recovery guidance — it does not mention that the backup can be retrieved via sieve_list_backups/sieve_get_backup, which would close the loop on the destructive operation.

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 'name', 'accountId', and 'accountName' are already fully documented in the schema, including the case-sensitivity and the list_scripts cross-reference. The description adds no parameter-level detail beyond what the schema supplies, so the baseline 3 applies.

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?

Opens with a specific verb+resource pair ('Delete a stored script from the server') that cleanly separates it from siblings like sieve_rename_script, sieve_put_script, and sieve_activate_script. The guard clause ('Refuses to delete the active script') further narrows scope so an agent knows exactly which deletions this tool will perform.

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?

Gives an explicit precondition for invocation ('Only when the user asks for the script to be deleted') and an explicit exclusion (the active script cannot be deleted). It does not, however, route the agent to the natural alternative workflow — deactivating via sieve_deactivate_scripts before deletion, or restoring from the returned backup via sieve_get_backup.

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