session_record_replay

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

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false. The description goes beyond this by detailing concrete real-world effects (re-sending messages, re-submitting forms, spending money), the high-risk classification with an approval prompt, the requirement that the tab must be open, and how partial replay failures are reported. This is exactly the kind of context an agent needs for a destructive action.

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 four information-dense sentences in a logical order: action, return behavior, prerequisites, and risk warning. Every sentence earns its place and there is 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?

Despite having no output schema, the return shape is fully disclosed. The description covers preconditions, failure reporting, real-world consequences, and safety gating. With only two parameters fully documented in the schema, nothing important is missing for correct invocation.

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 baseline is 3. The description restates that the session must be a stopped recording but does not add new meaning beyond what the schema already provides for sessionId or speed. No extra parameter-level guidance is given.

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 a specific verb (replay), a specific resource (a stopped recording), and the precise scope (in its original tab, reproducing interactions in order). It clearly differentiates from sibling record_* tools, which create, list, or inspect recordings, by focusing on the replay action.

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 gives clear context and preconditions: the recording must be stopped, the original tab must still be open, and the T3rnel Browser extension is required. It also warns that this acts on the live page and is gated behind an approval prompt, but it does not explicitly name alternative tools or stated when-not-to-use conditions.

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