Analyze prompt efficiency of recent sessions

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

Discloses that data is read on-demand and never stored, which is important for privacy. No annotations provided, so description carries full burden. Lacks details on authentication or rate limits but covers key behavioral traits.

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 efficient sentences: first states action and key behavioral note, second lists return values. No unnecessary words, front-loaded with important information.

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?

Describes purpose, behavior, and return values adequately for a simple tool, but misses documenting the 'dir' parameter and does not clarify how sessions are selected or what 'recent' means relative to limit. With no output schema, return values are listed but not detailed.

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 50% (limit has description, dir lacks it). Description does not explain the 'dir' parameter, leaving ambiguity. It adds context for limit through 'recent sessions' but insufficient for overall parameter clarity.

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?

Clearly states the tool runs an efficiency coach over recent Claude Code sessions, reads transcript text on-demand without storing, and returns specific metrics. Distinguishes from siblings by focusing on session analysis.

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?

Implies usage for analyzing recent sessions with a limit parameter, but does not explicitly state when not to use or compare with siblings like efficiency_score or estimate_impact.

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