Go back or forward

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

Annotations only supply readOnlyHint=false, so the description carries most of the burden, and it delivers the single most useful behavioral fact: the expected failure mode and its benign interpretation. It does not say what happens to the forward stack after a new navigation, nor what the call returns (no output schema exists), but the error semantics are the high-value disclosure here.

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?

Two sentences, no filler, with the core action and delta convention front-loaded and the failure-mode caveat appended where it is needed.

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?

For a 2-parameter tool with no output schema and minimal annotations, the description covers purpose, parameter convention, and the expected error case. Remaining gaps — return value and forward-history invalidation behavior — are modest but real.

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% and the delta property already documents 'Negative goes back, positive goes forward (e.g. -1 or 1)'. The description's '-1 is back, +1 is forward' largely restates the schema, though tying the failure condition to direction adds a little. Baseline 3 is appropriate.

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 — 'Move the active tab through its session history' — and even names the underlying API (browsingContext.traverseHistory). This is clearly distinguishable from siblings like browser_navigate or browser_activate_tab, which also move the active tab but for different reasons.

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?

Explains the delta semantics (-1 back, +1 forward) and, importantly, that a 'no such history entry' failure is a normal answer rather than a broken tool — that tells the agent when this call legitimately has nothing to do. It stops short of explicitly naming alternatives (e.g. use browser_navigate for new URLs instead of traversing), so no exclusion guidance.

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