Read a small site

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

Although annotations already declare readOnly/openWorld/non-destructive, the description adds substantial behavior the annotations cannot convey: robots.txt and Crawl-delay compliance, a single honest User-Agent, per-host pacing with backoff on 429/503, no login or cookies, and the return shape (JSON summaries plus a receipt). This is exactly the extra context structured fields cannot carry.

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?

Front-loaded with the trigger condition, then layered constraints and behavior with no filler sentences. It is dense--one very long compound sentence--but every clause carries operational information.

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 no output schema, the description compensates by stating the return (JSON page summaries and a receipt), and it covers safety, auth, and rate-limit behavior. The gap is same_host, whose purpose is never explained, and no hint of what the receipt contains.

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%, so url, depth, and page_budget are already documented in the schema. The description repeats the depth (0-3) and page budget (1-50) ranges rather than adding meaning, and same_host is left unexplained in both places. 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?

It gives a specific action and scope: 'agent needs several pages of one site', which is a real verb+resource, and the 'several pages' framing implicitly separates it from the sibling telos.crawl.fetch (single page). It stops short of naming that sibling outright, so an agent must infer the boundary.

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?

'Use when an agent needs several pages of one site' gives a clear triggering condition, and the description names the retrieval order (sitemaps and feeds before links). There is no explicit 'do not use this when...' or a named alternative such as crawl.fetch, so routing is left partly to inference.

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