list_roles

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

No annotations are provided, so the description carries the burden. The description accurately frames this as a list (read) operation and indicates roles have 'capabilities', giving some context about return semantics. However, it doesn't disclose details like whether filtering changes the output structure, or what new/unknown roles look like. For a read-only listing tool the bar is modest, but no annotations mean some disclosure is expected.

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 sentence that is front-loaded with the core action and purpose. It's appropriately concise with no filler. Could arguably add a usage note without bloating, but as written it is efficient.

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 read-only listing tool with zero required parameters and no output schema, this description is reasonably complete. The agent knows what action to take and roughly what to expect. However, given the large number of role-related siblings (manage_roles, transition_role, transition_role_workflow), a brief note about output format or what distinguishes roles listed here versus other role tools would improve completeness.

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 description coverage is 100% for the single parameter 'agentType', and the description adds the phrase 'by agent type' which semantically reinforces the filter but adds no new detail beyond the schema. The enum values (cursor, copilot, roocode, kilocode) are self-explanatory. There's a subtle mismatch since the description says 'List all... roles' but the parameter filters by agent type - the description doesn't clarify the relationship for the agent.

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+resource ('List all available Anubis roles') and mentions what's returned ('their capabilities'). It's clear enough, though it doesn't explicitly distinguish from the sibling 'manage_roles' tool which appears to be a CRUD operation on roles. The word 'all' signals listing scope.

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 implies this is a read-only listing tool, but provides no explicit when-to-use guidance or exclusions. Given the sibling 'manage_roles' exists for role management and 'transition_role' for changing roles, the agent might benefit from an explicit note about when listing is appropriate. Current guidance is only implied by the verb 'list'.

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