screen_record_start

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false. The description adds the key behavioral detail that recording is a persistent state that continues until screen_record_stop is called, which is genuinely useful beyond the annotations. However, it doesn't disclose the 180s device limit mentioned in the schema, potential storage implications, or what happens to an existing file at remotePath on restart.

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?

Two sentences total, each earning its place. The first states the primary purpose; the second clarifies the persistent nature of recording and its pairing with the stop tool. Zero wasted words, perfectly front-loaded.

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?

The tool has a coupled start/stop interaction requiring the agent to remember both the pairing and the remotePath location for later retrieval. The description adequately signals the pairing but doesn't explain the output schema, the retrieval flow via screen_record_stop, or the 180s duration cap that's buried in the schema comment. Given the output schema exists, not explaining return values is acceptable, but the start/stop workflow could use more scaffolding.

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 fully documents all three parameters (serial, duration, remotePath) with their descriptions and defaults. The description adds minimal value here beyond the schema, but the schema already does the heavy lifting with clear per-parameter documentation, so the baseline 3 applies.

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 verb (Start) plus resource (recording the screen), and distinguishes it from its obvious sibling screen_record_stop by noting recording continues until the stop counterpart is invoked. It's concise and unambiguous, though it doesn't mention specific output characteristics like the resulting file.

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 the paired start/stop interaction (recording continues until stop is called), giving the agent basic usage context. However, it doesn't explicitly state when to use this versus alternative capture mechanisms like screenshot, nor mention any preconditions such as device connection or permissions that might be required.

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