fetch_pages

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

With no annotations, the description carries the full burden. It discloses parallel fetching, return format (JSON with results and errors), optional JavaScript rendering, saving to a table, and the replace/append mode behavior. This covers the main behavioral traits. However, it does not mention potential side effects like whether saving to an existing table overwrites it (though mode explains this), nor rate limits or other constraints. Slightly more detail on error handling or table interactions would elevate it to 5.

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 paragraph but flows logically: core purpose, then key option, then batching guidance. It is not overly verbose for the complexity involved, though it could be broken into bullet points for clarity. Every sentence adds value, but the length might be slightly long. Still, it is well-structured and efficient.

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 description covers the major use cases: parallel fetch, JS-heavy pages, large URL batches via save_as, and batch replacement behavior. It also mentions the return format and follow-up with query_table. Given the tool's complexity (6 parameters, batching, parallel execution), it is complete enough for an agent to use effectively. The presence of an output schema (though not shown) and the description's hints at results/errors provide sufficient context.

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 0%, so the description is the sole source of parameter meaning. It explains js_render (for heavy JS), save_as (to write to a table), and mode (append vs replace). However, wait_ms and wait_for are not mentioned, and urls is self-explanatory. Since important parameters like batching are well explained but others are omitted, this is adequate but not comprehensive. A 3 reflects that it partially compensates for the missing schema 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 'Fetch many web pages in parallel', specifying the action (fetch), resource (web pages), and the batch nature (many, parallel). This distinctly differentiates it from the sibling 'fetch_page' tool, which likely handles single pages. The verb 'fetch' is specific and the scope (many pages) is unambiguous.

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 rich usage guidance: when to set js_render for JavaScript-heavy pages, when to use save_as for >20 URLs to avoid filling the conversation, and the exact pattern for batching with mode='append'. It also references the complementary query_table tool for further interrogation. While it doesn't explicitly say 'use fetch_page for single pages', the name and context imply that, and the instructions cover the key scenarios for this tool.

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