ck_outcome_tracker

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

The description correctly identifies record as a write operation and get_session/get_leaderboard as read-only, which aligns with the readOnlyHint=false annotation for the overall tool. It adds context about the feedback loop integration but does not elaborate on nondestructive or idempotent behavior. The description does not contradict any annotation.

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 a single paragraph but well-organized: first sentence states overall purpose, then breaks down modes, and ends with usage guidance. It is efficient with no redundant information. Could be slightly more scannable (e.g., bullet points), but remains clear and concise.

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 (three modes, eight parameters, integration with other tools), the description covers all essential context: what each mode does, which parameters are required, when to call, and why it matters. The presence of an output schema means return values don't need detailing here. Nothing is missing.

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?

While the schema covers 63% of parameters, the description adds significant context by mapping parameters to specific modes (e.g., session_id, outcome, agent_id, task_type for record; workspace_id, window, limit for get_leaderboard). It also specifies the acceptable values for outcome (success/partial/failure). This compensates for the schema gaps.

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 dual purpose: recording session outcomes and retrieving agent performance leaderboards. It distinguishes three modes with specific verbs: record (write), get_session (read), get_leaderboard (read). This differentiates it from sibling tools and leaves no ambiguity.

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 explicitly tells the agent when to call the tool ('after task completion before ending the session') and why ('so ck_route and ck_cost_optimizer have fresh performance data'). It also lists the required parameters for each mode, providing clear guidance on when to use which mode.

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