observe

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

With no annotations provided, the description carries the full disclosure burden, and it delivers meaningfully: it reveals two distinct operational modes (collect and until), the click-ordering guarantee ('click_first fires the triggering action after the observer is armed, so nothing is missed'), and the optional then_click behavior. It stops short of noting the internal polling fallback behind the interval parameter, though the schema documents that parameter.

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 sentences with the main purpose front-loaded in sentence one, followed by compact mode explanations. Every sentence earns its place; the 'so nothing is missed' clause captures an important ordering guarantee in four words without padding.

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?

The description covers the two execution modes and the click behaviors well, but the tool has no output schema and the description never states what the tool returns after a collect window or when an until condition fires. Constraint details like duration/until exclusivity and the polling-fallback behavior are left entirely to the schema. For an 8-parametter tool with zero annotations, this is adequate but not complete.

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 description coverage is 100%, giving a baseline of 3, and the description adds genuine value on top of the schema: it connects collect to duration, until to then_click, and clarifies the intent of click_first ('fires the triggering action after the observer is armed'). This conceptual grouping makes the parameter model understandable in a way the flat per-parameter schema descriptions alone do not.

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 action (watch an element for changes) on a specific resource (a DOM element via selector), and immediately distinguishes itself from the sibling evaluate tool ('instead of polling with MutationObserver/setInterval code in evaluate'). A new agent can tell what this tool does and how it differs from evaluate without opening the schema.

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 opening line gives a clear when-to-use signal: prefer this tool over hand-written MutationObserver/setInterval polling inside evaluate, which is a concrete alternative. However, the 'until' mode functionally overlaps with the sibling wait_for tool, and the description never mentions that alternative or states when not to use observe, so the routing guidance is incomplete.

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