search_conversations

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

With no annotations, the description carries the full behavioral burden. It does convey a read-style operation over stored conversations and mentions 'relevant content', which implies some relevance ranking, but it does not explain whether search covers full transcripts, metadata, summaries, or how results are ordered and limited.

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 a single efficient sentence with no filler and places the action and resource early. It earns its conciseness, though it is arguably too sparse to support tool selection among siblings.

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 input schema is simple and an output schema exists, so return structure may be covered elsewhere, but the tool sits in a crowded sibling set with multiple specialized search variants. The description does not explain when generic search is appropriate, leaving a meaningful selection gap for an agent.

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 description coverage is 0%, so the description must compensate for undocumented parameters, but it never mentions 'query' or 'limit' explicitly. The phrase 'relevant content' hints that query drives a relevance search and limit likely caps results, but that is inferred rather than stated.

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 states a specific verb ('search') and a clear resource ('stored Claude conversations'), so an agent can tell this is a search operation. It does not differentiate from sibling tools like search_by_topic, search_by_tag, search_by_session_id, or search_by_conversation_type, which all share the same search family.

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?

There is no guidance on when to use this generic search versus the specialized sibling search tools. With four search-by-* siblings plus get_search_stats, the description leaves the agent to infer which tool fits a given request.

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