get_interaction_log

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

No annotations are provided, so the description carries full burden. It mentions saving a JSON or CSV file and returning percentile stats, but does not clarify where files are saved (e.g., local vs. server) or whether there are side effects like file system writes. The phrase 'Periscope drove' may be unclear to external agents.

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 paragraph that front-loads the main purpose and then provides details. It is relatively concise given the complexity, though some sentences (e.g., 'Saves a JSON ... and returns percentile stats') could be more direct. Still, it avoids unnecessary fluff.

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?

There is no output schema, so the description should explain return values. It mentions returning percentile stats but does not specify their structure (e.g., keys like p50, p75). It also lacks prerequisites (e.g., session must exist) and error handling. The file-saving behavior is ambiguous (side effect or not?).

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 value by explaining the 'clear' parameter as 'Reset the recorded interactions after exporting' and specifying 'JSON is easiest to graph; CSV for spreadsheets' for format, which goes beyond schema enums.

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 it exports the real INP time series for a session, one record per interaction, with latency, event type, target, timestamp, and URL. It distinguishes from Lighthouse and mentions use after driving interactions, making the purpose specific and differentiated from siblings.

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 explicitly says 'Use after driving interactions (interact_and_test, click_element, fill_form…) and contrasts with Lighthouse, which cannot measure INP in lab mode. It also specifies ideal context: 'long interactive test where you want to see all INP times, not just the worst.'

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