fetch_pages

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: partial-failure tolerance ('individual failures do not discard successful extractions') and that only public pages are fetched, both of which matter for planning a multi-URL call.

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?

A single front-loaded sentence with no filler; the scope bound and failure behavior come first. It is arguably too terse for a tool with 0% schema coverage, but nothing is wasted.

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 no output schema and no schema descriptions, the description carries the full burden. It covers the URL cap and partial-failure semantics but says nothing about max_chars behavior or what the extraction results look like, so an agent cannot fully predict the call's outcome.

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 compensate. 'Up to 10' effectively documents a cap on the urls array that the schema does not express, but max_chars (default 12000) is never mentioned, leaving half the parameters undocumented.

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?

States a specific verb (Read) and resource (public evidence pages) with a scope bound (up to 10). The batch nature implicitly separates it from the singular sibling fetch_page, but the description never names that sibling or explicitly contrasts the two, so the differentiation is left to inference.

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?

There is no when-to-use or when-not-to-use guidance. An agent must infer from 'up to 10' that this is the batch variant and that fetch_page is for single URLs, but nothing in the text states that condition or names an alternative.

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