Replay recorded calls

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

Annotations already indicate destructiveHint=true, but the description adds no context about side effects, reversibility, or permission requirements. It mentions targeting a selected client, but this is more about parameters than behavioral consequences.

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 a single, concise sentence with no redundant words. However, its extreme brevity omits crucial operational details, preventing a perfect score.

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 that the tool is destructive, has no output schema, and has three parameters, the description is insufficient. It does not explain the meaning of sequences or stopOnError, nor the consequences of replaying calls. Sibling tools like recording_control suggest a broader workflow, but the description fails to provide that context.

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 only 33% (clientId has a description). The description adds some meaning for sequences ('up to 100 selected') and clientId ('original or a selected client'), but fails to explain stopOnError. This inadequate compensation for low schema coverage results in a low score.

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 tool's function with a specific verb ('Replay') and resource ('recorded RPC calls'), including scope ('up to 100 selected') and target ('original or a selected client'). This distinguishes it from sibling tools like get_recording and replay_remote_event, which handle different operations.

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 provides no guidance on when to use this tool versus alternatives, such as replay_remote_event or recording_control. It does not mention exclusions, prerequisites, or typical use cases.

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