Parallel Search MCP

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

Annotations provide readOnlyHint=true and openWorldHint=true, indicating safe read operations with open-world assumptions. The description adds context about extracting 'relevant content' and depth exploration, which hints at content filtering or summarization beyond raw fetching. However, it doesn't disclose rate limits, authentication needs, or specific extraction behaviors, leaving some gaps. No contradiction with annotations exists.

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 well-structured with a 'Purpose' section and bullet-pointed 'Ideal Use Cases,' making it easy to scan. Every sentence adds value without redundancy, and it's front-loaded with the core purpose. No wasted words or unnecessary details are present.

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 moderate complexity (fetching and extracting web content), annotations cover safety and world assumptions, and schema coverage is complete, the description provides adequate context. It clarifies use cases and distinguishes from implied alternatives. However, without an output schema, it doesn't describe return values (e.g., format of extracted content), which is a minor gap preventing a perfect score.

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 description coverage is 100%, with clear documentation for both parameters (urls and objective). The description doesn't add any parameter-specific details beyond what the schema provides, such as explaining how the 'objective' parameter influences extraction. With high schema coverage, the baseline is 3, and the description doesn't compensate with extra semantic value.

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's purpose as 'Fetch and extract relevant content from specific web URLs,' which is a specific verb+resource combination. It distinguishes from the sibling 'web_search_preview' by focusing on extraction from already-identified URLs rather than search. However, it doesn't explicitly contrast with the sibling in the purpose statement itself, keeping it at a 4 rather than a 5.

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 'Ideal Use Cases' section provides clear context for when to use this tool: for extracting content from specific URLs you've already identified or exploring URLs from web searches in greater depth. It implies an alternative (web search) but doesn't explicitly name the sibling tool 'web_search_preview' or state when not to use this tool, so it falls short of a perfect 5.

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

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

Annotations provide readOnlyHint=true and openWorldHint=true, indicating safe, open-ended operations. The description adds that results are 'LLM-friendly' and 'tuned for LLMs,' which offers useful context about output formatting and parameter optimization beyond annotations. However, it lacks details on rate limits, authentication needs, or result structure.

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 a single, efficient sentence that directly states the tool's purpose and key features. It is front-loaded with no unnecessary information, though it could be slightly more structured (e.g., separating purpose from format details).

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 (web search with 2 parameters), annotations cover safety and scope, and schema coverage is complete. However, there is no output schema, and the description does not explain return values or error handling. It adequately covers the basics but lacks depth for a tool that interacts with external web resources.

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 description coverage is 100%, with clear descriptions for both parameters. The description does not add any parameter-specific semantics beyond what the schema provides (e.g., it doesn't explain how 'objective' and 'search_queries' interact). Baseline 3 is appropriate as the schema adequately documents parameters.

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's purpose: 'Perform web searches and return results in an LLM-friendly format and with parameters tuned for LLMs.' It specifies the verb ('perform web searches') and resource ('results'), but does not explicitly differentiate from the sibling tool 'web_fetch' (which likely fetches specific URLs rather than performing searches).

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 provides no guidance on when to use this tool versus alternatives. It mentions the tool's purpose but does not indicate when it should be used over 'web_fetch' or other potential search tools, nor does it specify any prerequisites or exclusions for usage.

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