trawl_crawl_web

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

With no annotations at all, the description carries the full burden, yet it does not disclose that this performs network I/O and writes many pages, how long a crawl may take, whether existing pages are overwritten, or what happens on partial failure. Only the Markdown output destination is conveyed, and even that ('for a client') is ambiguous.

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?

One sentence with no padding is good front-loading, but it is under-specified rather than concise, and the trailing 'for a client' phrase adds confusion rather than 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?

For a multi-parameter, network-facing write tool with no annotations and no output schema, the description is far too thin: it omits crawl scope, pool semantics, limits, and return/failure behavior, leaving the agent to infer almost everything.

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%, so most parameter meaning comes from the schema itself and baseline 3 applies. The description adds nothing about pool_name (the schema merely says 'Pool name') or crawling scope beyond what stay_in_path and max_pages already declare.

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?

States a specific verb plus resource plus outcome: crawl a website and save pages as Markdown. An agent can tell what it does, but nothing distinguishes it from siblings like trawl_ingest_url, and the phrase 'for a client' is unexplained.

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?

There is no guidance on when to choose this over trawl_ingest_url or the search/ingest family, no preconditions (does the pool need to exist?), and no exclusions. An agent must guess from the sibling list.

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