mcp-research

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

Annotations cover safety profile (readOnly, idempotent, openWorld), but the description adds valuable workflow context (the 4-step pipeline) and quantitative expectations for depth levels (2/5/10 pages). No contradictions with annotations detected.

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?

Front-loaded with the core workflow summary, followed by structured Args documentation. Every element serves a purpose—no redundant text, no missing critical details. Well-structured for LLM parsing.

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 presence of output schema and rich annotations, the description appropriately focuses on workflow orchestration and parameter semantics. It fully compensates for the schema's documentation gaps and adequately explains the compound operation's behavior.

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?

With 0% schema description coverage, the description carries full documentation weight and succeeds completely: it defines 'query' as the research question, explains 'depth' values with specific page counts, and clarifies 'context' usage for synthesis continuity.

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 defines the tool as a compound operation ('search → fetch top pages → summarize → synthesize') that distinguishes it from sibling tools fetch_url and web_search. It uses specific verbs and explains the multi-step pipeline distinctively.

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 'Compound research' framing and explicit workflow pipeline provide clear context that this is for comprehensive research synthesis versus simple fetch/search operations. While it lacks explicit 'when not to use' statements, the scope differentiation from implied siblings is clear.

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