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

The description goes well beyond the readOnlyHint annotation, disclosing URL construction ('path=/ → index.txt; else path without leading slash + .txt'), response truncation ('summary = first 4000 chars; truncated=true if longer'), error mapping ('HTTP errors → ok=false'), and a content limitation for /review. This is exactly the behavioral context the annotation does not provide.

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 telegraphic but every clause carries a distinct fact: URL pattern, path mapping, truncation, error behavior, use case, caveat, and sibling routing. The WHAT/USE/NEXT labels make it easy for an agent to parse quickly. 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?

With an output schema present and readOnlyHint=true, return values and safety are already covered, and the description handles the rest: URL construction, truncation, error semantics, and a content caveat. The one residual gap is the unaddressed relationship to the similarly named sibling get_ai_txt, which an agent could easily confuse with this tool.

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 100%, so the baseline is 3, and the schema already documents both parameters with examples. The description adds value by explaining how path maps to the fetched file ('path=/ → index.txt; else path without leading slash + .txt') and how locale prefixes shape URLs, which is not stated in 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 opens with a specific verb and resource ('Fetches public https://www.ikeytz.com/ai-pages/{locale}/{file}.txt (HTML-parity fulltext)') and states what the tool is for ('USE for page content'). It also distinguishes itself from a sibling ('NEXT: get_serp_snippet for title/description only'). The only minor gap is that it never differentiates itself from the nearly identically named sibling get_ai_txt.

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?

Explicit guidance is present: 'USE for page content' states when to invoke it, and 'NEXT: get_serp_snippet for title/description only' names the alternative and the condition that selects it. The '/review has no HTML-parity footer' caveat further helps an agent avoid a wrong call.

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