Batch install

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the safety profile is partly covered. The description adds genuinely new behavioral facts: name and packages are effectively required despite the schema marking nothing required, and notes must be a string — details an agent cannot get from annotations or schema. It still omits whether the install is asynchronous, how progress is polled, and what side effects occur on the target instance.

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 lead sentence is short and front-loaded, which is good, but the rest is a pasted Sphinx docstring whose ':type X: str' lines merely restate what the JSON schema already encodes. It is neither bloated nor maximally efficient — redundant type tags dilute the few useful lines.

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 43-parameter mutation tool with no output schema, the description is far too thin. It does not describe the batch lifecycle (does it block, or is it polled via servicenow_batch_install_result?), what the returned Pydantic model contains, or how the many optional provisioning parameters interact — all information an agent needs before invoking it.

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?

The schema has 43 parameters at 0% description coverage, but the description documents only name, notes, and packages. The remaining 40 parameters (sys_id, scope, repo_url, update_set_id, auto_preview, rollback_install, force_commit, etc.) are entirely opaque, so the description falls far short of compensating for the coverage gap.

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 description states a specific verb and resource: 'Initiate a batch installation.' An agent knows this kicks off an install job. However, it does not distinguish this from close siblings such as servicenow_batch_install_result, servicenow_batch_rollback, or servicenow_app_repo_install, so the agent cannot tell which entry point applies without opening schemas.

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?

There is no when-to-use guidance, no prerequisites (auth, permissions, instance context), and no mention of alternatives or follow-up tools. The only usage-adjacent content is the raises clause, which says name/packages must be supplied, but it never frames this as a usage rule or workflow step.

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