self_improve

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

Annotations already mark readOnlyHint and idempotentHint. The description adds significant behavioral context beyond these: it details the internal steps, notes that if `text` is omitted it "runs tokenpull first (requires local ccusage logs)", and explicitly states "Pure local math — no network, no submission." It also clarifies scope behavior (daily never leaves machine; weekly distribution appears in report artifacts). This fully discloses safety and data handling.

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 lengthy but every sentence carries information. It uses a numbered step list to structure the pipeline, which aids readability. It could be slightly tightened (e.g., the scope explanation repeats some schema content), but overall it is appropriately sized for the tool's complexity.

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?

With a 5-step pipeline, 3 parameters, output schema present, and annotations available, the description covers the full usage context: when to call, what happens under different input conditions, scope variations, return value (cycle of diagnosis + suggestions + simulated impact), and safety highlights. It leaves no major gaps for an agent to misuse the 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?

Schema coverage is 100%, so baseline is 3. The description adds extra meaning for `text` (conditional skipping of tokenpull, requires local logs when omitted) and for `scope` (adds mode detection and scoped analysis options). It does not add new details for `window` beyond the schema, but the added conditions for the other two params raise it 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 opens with a specific verb+resource: "Runs the full self-improvement cycle in one call" and then enumerates the exact pipeline steps (gets pillars, diagnoses, generates suggestions, simulates, returns results). It clearly distinguishes itself from sibling tools that perform individual steps (tokenpull, diagnose_cascade, suggest_improvements, simulate_change) by branding itself as the "one-click optimize" orchestrator.

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 gives explicit when-to-use guidance: "call it at the end of a session to see what to improve next time." It also explains conditional usage based on input: if `text` is provided, tokenpull is skipped; if omitted, tokenpull runs and requires local ccusage logs. It even notes the `scope` options and their implications. While it doesn't explicitly list when NOT to use it, the guidance is clear and actionable.

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