Resume Recording

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false and openWorldHint=false, so the safety profile is carried by structured data. The description adds useful context that the original target and settings are reused, but it never addresses what is destructive about resuming (e.g., appending/overwriting the existing capture) nor any failure conditions.

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?

A single short sentence with the key constraint ('same target and settings') front-loaded. No filler.

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?

An output schema exists and annotations cover the safety profile, so the description needn't explain returns. It is nearly complete for a one-parameter lifecycle tool, with the only real gap being the unaddressed destructiveHint=true 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?

Only one parameter, and schema coverage is 100% with the description 'From start_recording.' The description adds nothing parameter-specific beyond implying the session determines target/settings; baseline 3 is appropriate when the schema does the work.

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?

States a specific verb (resume) and resource (a paused recording), and the parenthetical 'same target and settings' pins down that it continues the existing session rather than starting a new one. It is distinguishable from start_recording/pause_recording/stop_recording, though it never names them.

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 word 'paused' implies a precondition (the session must currently be paused) and the schema note 'From start_recording' ties the sessionId back to session creation. However, there is no explicit guidance on what to do if the session is not paused, or on why one would resume vs. start a new recording.

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