script_write

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

Annotations already flag destructive=true and idempotent=false, so the safety bar is partly covered. The description adds genuinely non-obvious behavior: atomicity on compile failure ('the previous script stays active'), the isError return signal, and optimistic concurrency via expected_sha256. It does not say whether the install is reversible or what permissions are required against the live table, leaving one meaningful gap.

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?

Five short sentences, each carrying distinct information: action, input constraint, concurrency check, failure semantics, follow-up. The action is front-loaded and nothing is repeated from the schema or annotations.

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-idempotent write to a live production script with 7 loosely documented parameters and no output schema, the description covers failure and concurrency well but leaves the targeting model unexplained. An agent cannot tell from this text whether it needs object or template_id for a given target, which is a real gap before invoking.

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 only 29%, so the description must carry weight; it does explain the code/file_path mutual exclusion and the purpose of expected_sha256, neither of which is documented in the schema. But the most consequential parameter, target (global/object/template), is never explained, and its interaction with object, template_id, and table_id is left entirely to inference.

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 verb+resource pair is concrete: 'Compile and install Lua source on the live table' tells an agent exactly what happens, and 'Read console afterwards' points at the follow-up. It stops short of distinguishing this from adjacent write paths such as table_command, blueprint_apply, or modules_import, which an agent could plausibly confuse with installing code.

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?

'Supply exactly one of code/file_path' and 'Read console afterwards' give a usable call recipe and a post-call workflow. However, there is no explicit statement of when to prefer this over sibling write tools, nor any precondition (connection state, permissions) that selects it. Usage is implied by the mechanics rather than stated.

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