get_capabilities

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

No annotations are present, so the description carries the full burden. 'Return' implies a read-only operation, but the description does not disclose the response format, whether the data is static or computed per call, or any potential cost/limitations. It adds some value by specifying the content type (versioned feature groups, compatibility) but lacks depth.

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?

A single concise sentence is front-loaded with the action and resources. Every word is informative, and there is no redundancy or filler. It is appropriately sized for the tool's simplicity.

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?

The tool is simple: no parameters, no output schema, and a clear (if brief) description. The description conveys the core purpose and return content. However, because there is no output schema, a bit more detail about the structure of 'feature groups' would make it fully complete, but it is sufficient for a no-param discovery tool.

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 tool has zero parameters, so there is little to explain. The empty input schema fully covers the parameter space. The description adds no parameter-specific details, but with no params, the baseline of 4 is appropriate.

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 'Return versioned feature groups and compatibility information' clearly states the verb (return) and the resource (versioned feature groups and compatibility info). It distinguishes from siblings like get_godot_version and get_server_info by focusing on capabilities rather than server/version specifics, though the term 'feature groups' is slightly vague.

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?

Usage is implied: call this tool to discover available capabilities and compatibility. However, no explicit guidance is given on when to prefer it over alternatives such as get_server_info or get_godot_version, nor any exclusions. The context of a no-param info tool makes this acceptable but not outstanding.

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