web_snapshot

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real behavioral context: deterministic, no image, a fraction of the tokens, and how find/max_depth narrow output. It stops short of covering auth/profile requirements or tier/timeout behavior, so it is strong but not exhaustive.

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?

Four tight sentences, front-loaded with the resource and output shape, then routing rules, then token cost rationale. No filler and nothing repeated from structured fields.

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 correctly explains the returned nodes and how to reuse a ref, which is the critical return-value information. It omits guidance on tier/profile/timeout that matters for a 7-param open-world tool, so it is complete but not fully so.

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 each of the 7 parameters is already documented in the schema; the description only restates find and max_depth semantics. Per the baseline rule for high coverage, this is a 3 with no compensating detail added.

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 and resource ('Read a page as its interactive structure: every button, link and field with its role, accessible name and a short ref') and names the siblings it displaces (web_fetch, web_screenshot). An agent can distinguish this from every other read-oriented sibling without opening a schema.

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?

Gives explicit conditions: use instead of web_fetch when the next step is to click or type, instead of web_screenshot when a page must be understood, and pass a ref to web_act or browser_do. Both the selection rule and the downstream handoff are spelled out.

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