search_claude_sessions

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions case-insensitive full-text search and returned fields (snippets, IDs, timestamps) but omits details on performance, rate limits, result ordering, or pagination behavior. The read-only nature is implied but not explicitly stated.

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 in the first sentence, followed by concise behavioral details and an Args block. It avoids fluff, though the Args section could be integrated more seamlessly. Overall efficient and well-structured.

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 tool's complexity (3 params, one required), the description covers purpose, match behavior, and all parameters. An output schema exists, so detailed return value documentation is not needed. No annotations exist, but the description is sufficient for a safe search operation. Missing: no mention of error cases or result ordering.

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 has 0% description coverage, so the description must compensate. It adds meaningful context for all three parameters: query is 'Text to search for', project_slug limits to a project (empty for all), and limit sets max hits (default 20). This goes beyond the schema's raw structure, though the query parameter could include case-insensitivity detail.

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 it searches for text across Claude Code session messages, specifying case-insensitive full-text search over user and assistant messages, and returning snippets with context, session IDs, and timestamps. This distinguishes it from sibling tools like get_claude_session (retrieve single session) and list_claude_sessions (list sessions).

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 implies usage when searching session text but does not explicitly state when to use this tool versus alternatives like get_claude_session for retrieving a specific session or list_claude_sessions for listing. No exclusions or prerequisites are mentioned, leaving the agent to infer usage context from sibling names.

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