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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered structurally. Beyond that, the description adds a genuine behavioral trait: the browser render is shared with render_page, so calling both costs one render, plus the option to supply a tree instead of a url. It does not discuss limits, rate constraints, or failure behavior when a page cannot be rendered.

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?

Three dense sentences, front-loaded with the core action ('Show a page the way a screen reader announces it'), and the operand list plus the render_page/tree notes are all actionable. It is on the long side, but nearly every clause carries distinct information, so little is wasted.

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 an output schema present, the return shape need not be restated, and the description nonetheless frames what the analysis surfaces (the accessibility problems it flags). The render-sharing relationship, the alternative tree input, and the scope of the inspection are all covered, leaving nothing an agent needs to invoke it correctly.

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 both url and tree are already documented, giving a baseline of 3. The description goes further by clarifying the intended use of tree: only when you have your own browser tool, and it should be that tool's accessibility snapshot. That conditional guidance is meaningfully more than the schema text alone.

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 (show), a specific resource (a page as announced by a screen reader), and enumerates the exact artifacts returned: landmarks, heading outline, and reading order of named links/buttons/images/form fields. It also names what it detects (unnamed controls, vague link text, unlabeled fields, missing main, skipped headings, hidden text), which clearly separates it from siblings like analyze_layout or render_page.

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 explains the relationship to render_page (shared render, so calling both costs one render) and gives an explicit alternative input path: pass your own browser's accessibility snapshot as tree. That is solid context for choosing between the two parameters, but it never states a when-not-to-use condition or a scenario where a sibling tool is the better choice.

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