Get Capabilities

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

With no annotations, the description carries the full burden, and it does disclose a key trait: 'Read-only', which is the safety profile an annotation would normally supply. It also describes what each mode returns (ids, names, binding summaries). It omits auth/permission and error behavior, so it is not fully exhaustive.

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?

Two short, front-loaded paragraphs with the list/single split clearly separated. Every sentence adds information and nothing is padded, though the parenthetical definition is slightly redundant with the title.

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?

An output schema exists, so return values need not be exhaustively explained, and the two required params plus the optional one are adequately covered. The description is complete enough to call the tool correctly, with only minor gaps around permissions and alternatives.

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 coverage is 67%: model_id and capability_id are documented in the schema, while server_version is not. The description clarifies capability_id's effect on the result shape, but that largely restates the schema's own 'omit to list every capability' note, and server_version remains unexplained.

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?

States a specific verb+resource (fetch a model's capabilities) and defines the term inline ('behaviours the feature must deliver'). It clearly separates the two modes (list all vs. single with bindings). It does not, however, distinguish itself from similarly-scoped siblings like get_control_objectives or get_functional_objectives.

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 gives mode-selection guidance tied to capability_id (omit to list all, provide for one with bindings), which is useful implied usage. It offers no guidance on when to prefer this tool over sibling capability/objective tools, and no prerequisites or exclusions.

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