Search Conversations

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds meaningful context about the search mechanism: it combines FTS5 full-text search, macOS Spotlight indexing, and optional vector similarity requiring Ollama. This goes beyond the annotations by explaining how the search works and its dependency on external components, without contradicting the annotations.

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 concise and front-loaded with the core purpose. It includes useful examples that illustrate query patterns without being verbose. The structure is clear, with a brief mechanism explanation followed by examples, making it easy to scan.

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 core search behavior, supported query types, and the dependency on Ollama for vector search. However, it does not explain the different search modes (auto, fts, spotlight, vector, hybrid) or the behavior when Ollama is not available. Given there is an output schema, return values are handled, but the description misses some operational details that would be useful for a tool with this level of 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 schema description coverage is reported as 0%, and the tool description only mentions 'project' and 'query' in examples without defining their semantics. It does not explain 'mode', 'limit', or 'response_format'. Although the schema itself provides descriptions for most parameters, the description fails to add meaningful guidance beyond what the schema already contains, especially for the 'mode' and 'limit' parameters which lack detailed explanation.

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 the tool's purpose: 'Search Claude conversation history using hybrid search.' It specifies a specific verb (Search), resource (Claude conversation history), and method (hybrid search), distinguishing it from sibling tools like cowork_history_list and cowork_history_get, which are for listing and retrieving rather than searching.

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 examples of different query types (natural language, keywords, exact phrases, and filters) which implies usage context, but it does not explicitly state when to prefer this tool over alternatives such as cowork_history_list or cowork_history_get. There is no mention of alternatives or exclusions, so usage guidance is only implied.

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