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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description and parameter docs add genuine behavioral context beyond that: the public-page restriction, the bot identifying itself as 'JohnsEssentialsBot' when user_agent is blank, robots.txt acknowledgment gated to the Business plan, timeout behavior, and the table_index error message when fewer tables exist. 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?

The description is a tight single sentence with the core action front-loaded. Minor deductions: the opening 'Extract Table —' duplicates the tool title, and the '[category: web]' tag is low-value metadata that adds noise rather than guidance. Otherwise efficient and well-ordered.

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 combination of the concise description and the unusually thorough parameter documentation covers the essentials for correct invocation: URL format, output shape, timeout limits, robot policy, and table selection errors. There is no output schema, but the output parameter adequately conveys the return format. The main gap is that the core description alone is thin; completeness relies heavily on the parameter docs.

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 100% and every parameter carries a rich description — output distinguishes JSON (feedable to next step) from CSV (one text block), timeout_ms gives a worked example, table_index explains error behavior, and acknowledge_robots clarifies plan gating. The main description adds little beyond the schema since the schema already does the heavy lifting, so baseline 3 is appropriate.

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 uses a specific verb ('Extract') plus a clear resource ('an HTML table from a public web page at a user-provided http(s) URL') and names the output forms ('JSON rows or CSV'). This cleanly distinguishes it from sibling tools like web_fetch and web_scrape_page, which handle general page retrieval rather than structured table extraction.

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 phrase 'public web page' implicitly scopes usage to publicly accessible pages, and the parameter docs reveal plan-gated behavior for robots.txt. However, the description does not explicitly name alternatives (e.g., web_fetch or web_scrape_page) or state when this tool is preferred over them. Usage context is implied rather than explicit.

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