what_can_you_do

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

The description explicitly states 'Read-only,' which is a key behavioral trait given the lack of annotations. It also mentions being 'Backed by the generated, versioned anatomy catalog,' implying the result is based on a static snapshot. It does not mention potential side effects like caching or rate limits, but the read-only disclosure covers the most important aspect.

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 well-structured into short, focused sentences: the opening purpose, conditional behavior with and without the parameter, a note about the underlying catalog, and the read-only flag. It is informative without being verbose, and every sentence earns its place.

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?

Given the tool's simplicity (one optional parameter, read-only, no side effects), the description covers all necessary aspects: what it does, how to use it, the parameter behavior, and the read-only nature. The output schema exists, so not describing return values is acceptable per the criteria.

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 only one parameter (`domain`) with no description, and the description compensates fully. It explains the meaning of the parameter by specifying what happens when it is absent ('returns a per-domain roll-up') and when it is provided ('lists the worker actions and connector capabilities'), including an example value. This adds substantial meaning beyond the bare schema.

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 purpose: 'Ask the Company Brain what it can do — capabilities & worker actions and their inputs.' It names the specific verb ('Ask'), the resource ('Company Brain'), and the output (capabilities and worker actions), making it unambiguous and distinct from other tools.

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 guidance on how to use the tool, including explicit behavior with and without the `domain` parameter and examples of valid domain values (e.g., 'finance', 'stripe'). However, it does not explicitly contrast this tool with sibling tools like `describe_anatomy` or `list_domain_actions`, so the 'when to use this vs alternatives' is only implicit.

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