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

With no annotations, the description carries the full burden and largely succeeds: it declares determinism ('no model'), the no-JS limitation, no link following, no robots.txt consultation, and boilerplate stripping (nav, footers, sidebars). It omits rate limits, failure/error behavior, and whether results are cached, leaving a modest gap for a network-bound fetch tool.

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 content is front-loaded with the core action and return shape, then transitions to constraints and exclusions. It is efficient overall, though the final clause trails off without punctuation ('sidebars '), which slightly hurts polish and readability.

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 usefully enumerates return fields (title, canonical URL, language, absolute links, content hashes) and the truncation/shape expectations. For a single-page fetcher it is nearly complete, with only error handling and rate-limit behavior 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 80%, so the schema already documents max_chars and the boolean defaults. The description adds a little framing (Markdown vs plain text output implying the format parameter, absolute links implying include_links), but it doesn't clarify include_tables or expand on truncation behavior beyond what the schema states. 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 gives a specific verb and resource ('Fetches one public web page') plus the precise output ('clean GitHub-flavored Markdown or plain text'), along with return fields. This clearly separates it from capture/rendering siblings like page-capture, and 'for agents that feed pages to a model' frames the resource scope tightly.

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?

It states a clear usage context ('for agents that feed pages to a model') and an exclusion ('does not run JavaScript (client-rendered pages come back sparse)'), which tells an agent when this tool will underperform. It stops short of naming an alternative for client-rendered pages or discussing rate/auth constraints, so it isn't a full when/when-not/alternative map.

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