get_children

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'List' implies a read-only operation, which is safe, but the description does not detail any potential side effects, error handling, ordering of results, or behavior for invalid refs. It adds minimal context beyond the obvious read nature.

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 description is extremely concise—two short clauses that immediately convey the core functionality and the optional filter. Every word earns its place, with no redundant or filler content.

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 relatively simple read-only tool with two parameters and no output schema, the description provides enough to understand its purpose and parameters. However, it omits mention of the return value format (e.g., an array of child instances) and any edge-case behavior. Given the tool's simplicity, this is adequate but not exhaustive.

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 description explicitly mentions both parameters: 'by ref' explains the required ref parameter, and 'Optionally filter by className' clarifies the purpose of the classFilter parameter. This adds meaning beyond the schema, though the slight naming mismatch (className vs classFilter) could cause minor confusion.

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 clearly states the tool's function: 'List the direct children of an instance by ref.' It specifies the action (list), the resource (direct children), and the distinguishing factor (by ref, as opposed to siblings like get_root or get_properties). The optional filter adds additional specificity.

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?

The description provides clear context for when to use the tool—when you need to list direct children of a specific instance. It mentions an optional filter by className, which gives a hint of usage scenarios. However, it does not explicitly mention when not to use it or suggest alternative tools for recursive traversal or other related operations.

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