record_session

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

With no annotations, description bears burden. It explains recording video, return format, and step compatibility. Could mention session management or side effects, but overall clear.

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 efficient sentences: first states purpose, second clarifies steps format, third provides usage guidance. No unnecessary words.

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?

Covers output, steps format, project behavior. Lacks potential limits like max recording length or error handling, but adequate given schema coverage.

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 covers all 3 params with descriptions. Description adds value by clarifying steps format (same as interact_and_test) and project parameter behavior (shared vs isolated context).

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?

Description clearly states the tool runs steps while recording a video and returns .webm file path. It distinguishes from interact_and_test by specifying that it's for visual artifact/repro, not assertions.

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 says to use for visual artifact/repro and to use interact_and_test for assertions/checks, providing direct contrast and guidance.

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