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

Annotations already declare readOnly and non-destructive, so the description's job is to add context, which it does: ref lifecycle ('Refs stay valid while the element exists') and diff semantics are genuinely useful. It omits truncation behavior, even though the cursor parameter implies the tree can be cut off.

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 compact clauses, front-loaded with the output description, then ref semantics, drag marking, and diff mode. No filler sentences and every clause carries 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 must describe the return value and does so well (compact tree, refs, drag markers). Truncation/cursor continuation is left entirely to the schema, a minor gap given the 20000-char cap.

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 every parameter including mode, scope, cursor and max_chars is already documented. The description only reinforces mode=diff and the ref convention, adding little beyond the schema, which is the expected baseline 3.

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 resource and output shape: 'Current page as a compact tree' with interactive elements tagged ref=eN. It clearly conveys what an agent gets back, but never names siblings like screenshot or extract to sharpen the boundary between them.

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?

Usage is only implied: the ref=eN scheme tells the agent this is the tool to call before click/type/select, and mode=diff hints at incremental polling. There is no explicit 'use this when X, use screenshot/extract instead when Y' guidance.

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