web_fetch

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool does NOT summarize or modify content, returns original text with specific elements, and explains that different engines (llm vs tavily/firecrawl) have different capabilities and dependencies (e.g., anti-bot handling, API keys). This provides solid insight into behavior beyond the basic fetch action.

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 appropriately structured with sections for Returns and Notes, and each sentence provides useful information. It is slightly longer than many tool descriptions, but given the need to explain engine options and output format, it is not bloated. The main action is stated upfront.

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?

The absence of an output schema means the description must explain return values, and it does so thoroughly with a detailed Returns list (metadata, table of contents, content structure). It also covers engine behaviors and limitations. For a tool with two parameters and moderate complexity, all essential context is present.

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 coverage is 100%, so baseline is 3. The description adds meaningful semantics: URL must be valid and accessible, and the fetch_engine parameter is explained in depth (default via FETCH_ENGINE env, llm model-based, tavily/firecrawl dedicated crawl with API key requirements). This goes beyond the schema's brief descriptions.

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: 'Fetches and extracts the complete content from a specified URL and returns it as a structured Markdown document.' This uses a specific verb and resource, and the output format is explicit. However, it does not explicitly distinguish itself from sibling tools like 'web_search', so it misses the top score for sibling differentiation.

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 implied usage context by explaining what kind of URL is acceptable (valid HTTP/HTTPS, not behind auth) and mentions engine choices, but it does not explicitly state when to prefer this tool over alternatives like web_search. There are no direct 'when to use' or 'when not to use' instructions, so it stops at implied usage.

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