scrape_websites

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

With no annotations provided, the description carries the full disclosure burden and conveys several real behaviors: content is persisted ('store their content'), api_key falls back to an environment variable when None, formats default to both markdown and html, and the return of only 'successfully scraped' providers implies partial failures are tolerated rather than raised. It omits storage destination, overwrite/idempotency behavior, and rate limits, but the disclosed traits cover the most decision-relevant runtime behaviors.

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 ~70-word description front-loads the purpose into one sentence and then uses a clean Args/Returns layout. Every line adds information, and nothing duplicates the schema, which contains no descriptions to repeat.

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?

All parameters and the return value are specified, which is solid for a three-parameter tool with a nested object. However, the description omits when-to-use guidance relative to extract_scraped_info and leaves 'store their content' ambiguous about where content is persisted and what side effects an agent should expect, so an agent must infer the pipeline relationship.

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 0%, so the description must supply all parameter meaning, and it does for all three parameters: websites is defined as provider_name→URL mappings, formats is constrained to ['markdown', 'html'] with a stated default of both, and api_key's None-means-environment-variable behavior is explained. This fully compensates for the empty schema.

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 states a specific verb and resource: 'Scrape multiple websites using Firecrawl and store their content.' The action is unambiguous, and the mention of storage clarifies that this tool is the ingestion step of a scrape-then-extract pipeline. It does not explicitly name sibling extract_scraped_info, but 'scrape and store' vs. 'extract info' makes the differentiation readily inferable.

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?

No guidance is given on when to call this tool versus the sibling extract_scraped_info, nor on whether the two are sequential stages or alternatives. The description covers mechanics but provides no selection context, exclusions, or prerequisites beyond the optional api_key, leaving the agent to guess the pipeline relationship.

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