ck_delegate

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

No annotations are provided, so the description carries full burden. It discloses that the tool mutates session state and describes four modes, but lacks details on post-delegation behavior, reversibility, authentication requirements, or what happens to the original session. This is adequate but not comprehensive.

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, starting with the primary action and then detailing modes and usage flow. It is relatively concise but could be tightened slightly by removing redundant phrasing (e.g., 'prefer' used twice). Still, it effectively communicates key information without excessive verbosity.

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 complexity (5 parameters, 4 modes, no output schema), the description covers the main aspects but leaves some gaps. It does not describe the return shape or what happens after delegation (e.g., confirmation, error handling). Completeness is moderate.

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?

With 80% schema coverage, baseline is 3. The description adds value by explaining the agent parameter as a target agent ID, enumerating the four modes with brief explanations, and clarifying session_id/task_id for correlation. This extra context justifies a score above baseline.

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: handing off a governed task to another AI agent while transferring governance context. It explicitly lists four operation modes and distinguishes itself from the sibling tool ck_route by specifying when to use each.

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 direct guidance on when to use ck_route (recommendation only) vs. ck_delegate (ready to hand off execution). It also mentions calling ck_route first to identify the best agent, giving clear context for proper usage.

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