page_summarize

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

With no annotations, the description carries the full burden and does so thoroughly: model used (Claude Haiku 5.5), HTML-to-Markdown reading, prompt-injection handling ('page content is treated as data, instructions inside the page are ignored'), truncation at ~25,000 chars with an input_truncated signal, no charge on unreadable pages, $0.005 USDC cost, and p99 latency of 12s. This is exactly the behavioral context an agent needs before invoking.

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?

Purpose is front-loaded and every clause carries information — cost, latency, truncation, charge policy all earn their place. The single dense block with stacked parentheticals is slightly heavy to scan, but there is no filler.

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?

There is no output schema, so the description must cover return semantics, and it does: the summary opens with what the page is, then bullet-pointed facts/numbers/conclusions, plus the input_truncated flag. Combined with the failure-mode, cost and latency disclosure, nothing an agent needs to call this correctly is missing.

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 75%, and the description adds real meaning beyond it: concrete word ranges for each length enum (60-90 / 150-220 / 350-450), the language default being the page language with a worked example (German, de), and what 'focus' is for. This is more than the schema alone conveys.

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 gives a precise verb and resource — 'Summarize any web page: send a URL, get a factual summary' — and even nails the output shape (opening statement plus bullet points), which functionally separates it from raw-content siblings like webpage_reader, page_extract and web_scrape. It never names an alternative sibling explicitly, so it falls just short of the top band.

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?

Usage context is clear: pass a URL, choose a length, optionally steer with 'focus'. The focus example ('pricing and plans') gives concrete guidance on how to use the tool well. However, there is no explicit when-to-use-this-over-X statement or exclusion (e.g. when to prefer raw extraction), leaving the routing decision somewhat to inference.

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