Read a web page or PDF

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds behavioral context beyond annotations: it specifies that only main content is extracted, that query filters passages, that section selects from an outline, and that long pages provide an outline and next_start for pagination. No contradiction with annotations.

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?

Three sentences, each earning its place. The core purpose is front-loaded, then query/section behavior is explained succinctly, and default behavior and pagination are covered. No filler or redundancy.

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 main behaviors: main content extraction, query filtering, section selection, start behavior, and pagination hint. An output schema exists, so return format details are likely covered there. Minor gap: max_chars behavior is not explicitly described, but it's in the schema with a default. Overall, the description is complete enough for an agent to use the tool correctly.

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 80% (4 of 5 params documented), so baseline is 3. The description adds significant meaning for query (filters passages) and section (selects from outline) beyond the schema's minimal descriptions. It also clarifies start behavior ('Otherwise from start') and mentions pagination via next_start, adding value beyond the 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 ('Reads') and resource ('a URL') and immediately clarifies output format ('clean Markdown (main content only)'). It also distinguishes from siblings by explaining query, section, and start behaviors, making the tool's purpose 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 explains how to use query, section, and start parameters but does not explicitly state when to use this tool versus siblings like find_in_page, page_links, or page_outline. The usage context is implied through the description of behavior, but no exclusions or alternative recommendations are given.

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