read_page

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

Annotations already mark the tool as read-only and idempotent. The description adds valuable behavioral info: cost warning ('expensive on large pages') and practical advice about token usage for HTML, which annotations do not cover.

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 slightly long but highly informative and well-structured: first sentence states purpose, then emphasizes read-only, recommends a mode, and warns about cost with alternatives. Front-loaded with key info.

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?

Given the tool's complexity (multiple output modes, cost implications, alternatives), the description covers all essential aspects: what it does, when to use each mode, what to avoid, and how to use parameters like save_to. No output schema exists, but the description implies return of content or path.

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 covers 100% of parameters with descriptions. The description adds semantic value by explaining the trade-offs between modes (e.g., markdown being cheaper than HTML) and suggesting default usage, going beyond mere enum listing.

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 'Read the page as text (default), markdown, raw HTML, or accessibility tree' with a specific verb and resource. It distinguishes from siblings by explicitly naming alternatives like extract_table, extract, and get_interactives.

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 explicit guidance: recommends markdown as the 'right middle ground', warns against using HTML on large pages, and directs users to other tools for tabular or repeated content and interactive elements.

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