Open the research RAG explorer (UI)

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

Annotations declare readOnlyHint=true, but the description adds significant behavioral context: the tool returns HTML that must be written to a file and used with create_artifact/update_artifact, and the mcp_tools array must be used verbatim to avoid allowlist errors. No contradiction with 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 front-loaded with the core purpose and provides essential context, usage examples, and procedural instructions. It is slightly lengthy but each sentence adds value, making it effective without being 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 no parameters, no output schema, and annotations covering read-only nature, the description is comprehensive. It explains the return type, artifact usage, MCP tool requirements, and related tools. Minor omission: no error handling details, but overall sufficient.

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 zero parameters, so no parameter description is needed. Baseline score of 4 applies as there is nothing to explain beyond what the schema provides (schema_description_coverage=100%).

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 returns the Research RAG Explorer UI as a self-contained HTML document, ready to render as a Cowork artifact. It distinguishes this from hand-written explorers and relates to sibling tools like add_kb_doc, rag_search, and search_kb.

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 usage examples are given: 'show/open the RAG', 'what's in the knowledge base', 'let me query the research index'. Negative guidance is provided: 'Do NOT hand-write your own explorer'. Instructions for artifact handling are also included.

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