session_extract

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

With no annotations, the description carries full burden and does well: it states the tool reads session files, summarizes them, uses Haiku to extract specific insight types, and stores results in memory. It falls short of detailing potential side effects or exactly how memory storage behaves, but the core behaviors are transparent.

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 sentences, front-loaded with purpose, no wasted words. The first sentence states what it does; the second adds process and usage context.

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?

The description covers the main workflow and usage timing, but it does not specify what the tool returns (no output schema exists) or elaborate on the 'stores in memory' behavior (e.g., which memory store, overwrite policy). These gaps are notable but not severe given the tool's moderate complexity.

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?

The input schema already documents hours_back with 100% coverage ('How many hours back to look for transcripts (default 24)'). The description adds no additional parameter meaning, so the baseline of 3 applies.

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 a specific verb and resource: 'Extract insights from recent Claude Code session transcripts (JSONL logs).' It distinguishes itself from sibling tools like memory_search or docs_ingest by focusing on session transcripts and a specific pipeline (read, summarize, extract via Haiku).

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?

Provides explicit context with 'Run during daily reflection,' telling the agent when to use it. However, it does not mention when not to use it or alternatives, so it misses the highest mark.

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