chrome_web_content_interactions

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds context: operates on loaded trace, returns metadata-first JSON, explains row_count and truncation flags, and handles empty results. No contradictions.

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 detailed but well-structured in concise paragraphs, with purpose front-loaded. Slightly longer than necessary but still efficient.

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?

Given no output schema, the description covers return format (JSON with metadata, row_count, truncated flags, empty result handling). It provides complete context for an agent to understand the tool's behavior.

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 3. Description adds value by stating default (100) and cap (5000) for limit, and explaining max_string_len as a character cap for returned rows, which is not fully detailed in the schema.

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 states it ranks Chrome web content interactions by total_duration_ms, listing specific columns and explicitly noting read-only. It differentiates from siblings by being Chrome-specific and referencing execute_sql for filtered queries.

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?

Explicitly states when to use (INP analysis, reproducing user-felt latency, finding slow handlers) and when not to use (non-Chrome traces will error). Also provides an alternative for filtered interactions via execute_sql.

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