search_threads

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

With no annotations, the description carries full burden. It discloses hybrid mode loads an embedding model (performance cost), returns snippets and threadId, and implies index-based search. No destructive behavior expected.

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?

Three well-structured sentences. First sentence states purpose, second explains modes, third gives usage advice. No waste.

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?

Covers search behavior, output, hybrid option, and source filter. No output schema but describes return format. Lacks explicit pagination or ordering details, but acceptable for a search tool given sibling tools cover other retrieval needs.

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 coverage is 100%. The description adds context: default keyword search, hybrid meaning on-device semantic similarity, and sources filter meaning. This adds moderate value beyond 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 it searches across multiple AI coding-agent tools and returns matching threads with snippets and threadId. It distinguishes from siblings like get_thread (fetch specific thread) and search_current_project (project-scoped).

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?

Explicit use case: 'recall past decisions, prior solutions, or earlier discussion before redoing work.' It explains keyword vs hybrid modes but doesn't explicitly exclude scenarios or name alternative tools for when-not-to-use.

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