Memory

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

Annotations declare readOnlyHint=true, but the description says snapshot is saved as a .heapsnapshot file and that gc can collect garbage first. Saving a file and forcing GC are side effects, which contradicts the readOnly annotation.

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 compact with no filler, but it is a single telegraphic fragment with awkward quoted action labels and it begins with action details rather than a clear tool-level summary.

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 does enough by listing what counters returns and what snapshot produces. It could be stronger by stating snapshot output shape or failure behavior when the DevTools channel is unavailable, but it covers the essential call context.

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 description still adds action-specific meaning beyond the enum labels: counters lists the exact metrics, snapshot explains the heapsnapshot output and summary, and gc is described as defaulting to true for snapshot. tabId is not expanded, but the schema already documents it.

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 names two concrete actions and specifies what each does: counters measures heap size, DOM nodes, documents, frames and event listeners; snapshot captures a heapsnapshot and summarizes object classes and detached DOM nodes. It is clear, but it does not distinguish the tool from nearby siblings such as perf_metrics, dom_inspect, or coverage.

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 only explicit usage constraint is that snapshot needs the full DevTools channel. There is no explicit when-to-use guidance for choosing counters versus snapshot, nor any comparison to alternative diagnostic siblings.

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