Surf Web

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

Annotations already indicate readOnlyHint=true and destructiveHint=false, so the tool's safety profile is known. The description adds useful context such as converting to 'LLM-friendly markdown' and targeting 'crypto-related' content, which is helpful. However, it does not disclose potential limitations, rate limits, or behavior beyond what annotations imply.

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 reasonably sized and structured with a purpose statement and a Commands section. However, it redundantly states 'Fetch and search web content' immediately before detailing the fetch command, and the search functionality is not properly documented. The structure could be tightened.

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 0% schema coverage and no output schema, the description carries the full burden. It details fetch parameters but omits search parameters, return format, error behavior, and any usage caveats. The tool's complexity (multiple operations) is not fully covered, leaving gaps for the agent.

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 no parameter descriptions (coverage 0%), and the description only lists parameter names (url*, target_selector, etc.) without explaining their meaning or format. For example, 'target_selector' is left ambiguous. The description partially compensates by listing names, but it lacks the depth needed for confident invocation.

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 'Fetch and search web content' and 'Retrieve any URL and convert it to clean, LLM-friendly markdown'. It distinguishes itself from sibling tools by focusing on general web data rather than a specific domain (e.g., surf_dex, surf_token). The verb+resource combination is specific enough, though 'web data' is broad.

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 opening line 'Use this when the user needs web data from Surf' provides a clear usage context. However, it does not explicitly mention when not to use this tool or alternatives like surf_news or surf_token. The command list gives some guidance (fetch for web page fetching) but lacks a search command, despite search being mentioned in the description.

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