mcp-research

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

Complements annotations well by disclosing the 3-tier cascade fallback mechanism and external dependencies (Brave, DuckDuckGo, scraper, Ollama). This helps the agent understand potential latency, failure modes, and that results may come from different sources. No contradiction with readOnlyHint/idempotentHint 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?

Efficiently organized with the operational summary front-loaded, followed by the Args block. Every sentence conveys essential information about the cascade mechanism or parameter semantics. The structured Args list is necessary given the lack of schema descriptions.

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?

With output schema present, annotations covering safety profiles, and the description fully documenting parameters and behavioral mechanics (cascade, fetching), the definition is substantially complete. Minor gap: could mention rate limits or typical response time given the multi-provider approach.

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?

Comprehensively compensates for 0% schema description coverage by documenting all 4 parameters in the Args block. Adds valuable constraints (1-20 range for max_results) and conditional dependencies (Ollama availability for summarize) that are absent from the schema's bare type definitions.

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?

States specific action (Search) and resource (web) clearly. The 3-tier cascade detail (Brave → DuckDuckGo → scraper) precisely defines the implementation mechanism. However, it does not explicitly differentiate from sibling tools 'fetch_url' (direct URL fetching) or 'research' (likely comprehensive analysis), leaving ambiguity about when to select this versus alternatives.

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?

Provides no guidance on when to use this tool versus the 'research' or 'fetch_url' siblings. Does not explain when to enable 'summarize' or 'auto_fetch_top' flags versus making separate tool calls. No mention of prerequisites like internet connectivity given the openWorldHint.

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