security_change_script

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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: safe statement ordering (creates, grants, revokes, drops) unless keep_order, header contents, warnings emitted as '-- WARNING:' comments, no privileges required, and password handling (placeholder '<set password>'). This is exactly the kind of behavioral context the annotation does not carry.

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?

The read-only/for-review framing is front-loaded and every sentence adds a distinct behavioral fact. It is dense with parentheticals and backticked literals, which is slightly heavy, but nothing is redundant.

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?

With no output schema and only a readOnlyHint annotation, the description carries the full burden and does so: it explains what is produced (a script with a header and warning comments), what it does not do (run anything, take privileges, handle passwords), and the ordering behavior. An agent has enough to call it correctly.

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 0%, so the description must compensate, and it largely does: 'actions' is defined as the same object used for security_change_plan, and 'keep_order' is explained as keeping the given order rather than the safe order. The internal shape of each action object is still left to the sibling tool, so it is helpful but not fully self-contained.

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?

Starts with a specific verb+resource+scope: 'one or more changes as a SQL script for review... instead of running them.' It explicitly differentiates itself from execution siblings via 'The statements are what Run would execute' and 'Runs nothing,' so an agent can distinguish it from security_change_apply/security_change_plan 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?

It clearly frames the use case (produce a script for DBA review rather than execute) and cites the alternative by name ('the same object as for security_change_plan'). It stops short of naming security_change_apply directly or stating explicit when-not conditions for all siblings, so it is strong but not exhaustive.

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