recall

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

No annotations provided, so description carries full burden. It details hybrid search, scope, filter formats, return fields, scoring (recency/kind-weighted, normalized RRF), and ID stability (ephemeral summary IDs), leaving no ambiguity.

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?

Concise (~6 sentences) with front-loaded purpose, well-structured layout, no fluff. Every sentence adds value.

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 presence of an output schema, the description still provides complete context: scoring details, ID stability, and links to sibling tools. Covers all aspects for correct invocation.

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 has 0% description coverage, but description compensates by explaining scope values, since/until format, and project matching. The 'k' parameter is only given a default but not explained (e.g., number of results), a minor gap.

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?

Description clearly states 'Search past Claude Code sessions (episodes), memory notes (memories), and per-session digests (summaries...)' with specific verb and resources. It distinguishes from siblings like 'get_episode' and 'remember'.

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?

Explains when to use this tool (searching across multiple kinds of data), scope options, filters, and even notes about ID stability and fallback to 'get_episode' for full text, giving clear guidance.

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