recall

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

No annotations provided, so the description carries full burden. It discloses auto-routing behavior, session-first caching, and fallback to knowledge graph. There is a minor contradiction with the input schema: description mentions top_k default of 10, while schema shows 15. This is not an annotation contradiction but a factual error. Overall, behavioral traits are well explained.

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 front-loaded with the core purpose, followed by a clear parameter list. It is slightly redundant (auto-routing mentioned twice) and contains a default value inconsistency (10 vs 15). Still, it is well-structured and not overly verbose.

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 6 parameters, 1 required, and no output schema, the description covers the search process, routing logic, and parameter details. It lacks explanation of the return format or output structure, which would be helpful for a search tool. Overall, it is fairly complete but has a minor gap.

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?

Input schema has 0% description coverage, so the description must compensate fully. It provides detailed explanations for all 6 parameters, including the purpose of each, options for search_type, and the role of session_id in session-first search. This adds significant value beyond the bare schema.

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 'Search memory' as the primary action, with auto-routing and session awareness. This distinguishes it from sibling tools like 'remember' (store) and 'forget' (delete). The verb and resource are specific.

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 explains when to use it (searching memory) and provides context on auto-routing and session cache fallback. However, it lacks explicit when-not-to-use guidance or comparison with alternatives like 'search' tools in other contexts. The guidelines are clear but not exhaustive.

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