Page Snapshot

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

Annotations only cover the safety profile (readOnly, idempotent, openWorld, non-destructive); the description adds substantial behavior beyond that: ref stability across snapshots, re-resolution by role and name for re-rendered elements, the explicit failure mode when an element is truly gone, shadow-root and same-origin iframe traversal, hidden-subtree skipping, name capping at 100 chars, and an untrusted-data warning.

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 purpose and a format example, then usage, then edge-case behavior — no filler sentences. It is dense and somewhat long, but the length is justified by a 7-parameter tool with no output schema; a couple of behavioral clauses could be tightened.

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 carries the return-format burden and does so: it shows the tree line format, explains refs, truncation reporting, and diff output ('unchanged' vs added/changed/removed). Combined with the per-document ref caveat and untrusted-data warning, an agent has everything needed to call and interpret it.

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 100%, so the baseline is 3; the description goes further by explaining how refs are consumed as selectors and by steering parameter choice ('Prefer interactive_only...', 'diff to see only what changed'). It adds practical semantics for diff and interactive_only beyond their schema text, though depth, boxes, scope and max_chars are left to the schema.

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 the page as a compact tree of roles, accessible names and refs' — and immediately shows the output shape with a concrete example (`- button "Save" [ref=e12] (disabled)`). This clearly separates it from get_page_content, get_html, query_elements and screenshot, all of which expose the same page differently.

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 actionable routing: pass a ref as the selector of click, fill, select_option, press_key, scroll, query_elements, wait_for_selector or get_page_content, and explicitly recommends interactive_only for 'a menu of things to click' and diff for change detection. It also flags the navigation caveat (refs are per document, snapshot again). It stops short of stating when to prefer a sibling like get_page_content or get_html over snapshot.

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