performance_stop_trace

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

Annotations include readOnlyHint=false, which correctly indicates this is a mutating/state-changing operation (stopping a recording). The description adds the behavioral context that it stops an 'active' recording, implying it may fail or no-op if no trace is active. However, it doesn't disclose what happens to the collected data, whether it must be saved via filePath, or any side effects on the page. With annotations present, the bar is lower, and the description adds some context beyond the 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 a single, concise sentence that front-loads the action and target. It earns its place with no wasted words. It could add a note about filePath or prerequisites, but for its length it is well-structured.

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 simple stop operation with one required parameter and full schema coverage, the description is mostly complete. However, it doesn't clarify the relationship with performance_start_trace (e.g., must a trace be active?), nor what happens if no trace is active, nor whether filePath is required to persist the trace. The output schema is absent, so the description could have explained what the tool returns, but for a stop action this is a minor gap.

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%, so the schema already documents both parameters. The description doesn't add meaning beyond the schema, but the schema itself is clear: pageId targets a page, filePath specifies where to save trace data. The description's mention of 'trace recording' implies filePath is for saving the trace, but it doesn't clarify whether filePath is required to save data or optional. Baseline 3 is appropriate given full schema coverage.

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 action ('Stop the active performance trace recording') and the target ('on the target webpage'). It distinguishes itself from performance_start_trace by the verb 'stop' vs 'start', though it doesn't explicitly name the sibling. The resource is clear enough for an agent to understand the tool's function.

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 implies usage: it should be used when a performance trace is active and needs to be stopped. It doesn't explicitly state when to use it vs alternatives, but the sibling context (performance_start_trace) makes the pairing obvious. No explicit exclusions or prerequisites are mentioned, such as needing to have started a trace first.

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