test_keyboard_navigation

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

No annotations are provided, so the description carries the full burden. It discloses the process (tabs from top, records focus order, flags issues) and the return values (total_tab_stops, focus_order, issues). However, it does not state whether the tool is read-only or if it has side effects on the session, which would be helpful for a test 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 description is concise with three clear sentences. The first sentence immediately states the main action, followed by return values and a brief note on usage. No redundant 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?

Given no output schema, the description adequately explains return values (total_tab_stops, focus_order, issues). It covers the tool's purpose and input options. However, it could mention prerequisites or expected behavior when no focusable elements are present.

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 baseline is 3. The description adds meaningful context beyond the schema by explaining the 'project' parameter's impact on authentication context and clarifying that 'url' or 'session_id' can be used. This helps the agent understand parameter choices better.

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 clearly states the specific action ('Tab through a page from the top and record the focus order, flagging any stop with no visible focus indicator') and identifies the resource (keyboard navigability audit). It distinguishes from siblings by mentioning it works on a session or URL and focusing on keyboard operability, which is unique among the listed tools.

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?

The description indicates when to use the tool ('works on a session or a URL') but does not provide explicit exclusions or alternative tools. Sibling tools like 'test_responsive' or 'check_color_contrast' have different purposes, but no guidance is given on choosing between this and other accessibility tests.

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