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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower; the description still adds real context by noting the returned hash is identical at any replay speed and by enumerating the recorded contents. It does not discuss volume, ordering guarantees, or failure modes when no replay exists.

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, front-loaded with the verb and scope, then the usage cue. The content list is dense but each element earns its place; 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?

There is no output schema, so the description carries the burden of describing return values, and it does so by enumerating the record types plus the recording hash. Adequate for a read tool with fully documented parameters, though it omits result size/format expectations.

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 100%, so both parameters are documented in the schema; the description's enumeration of tape/strategy/user/move content loosely corresponds to the 'kinds' filter but never maps to the enum tokens (slot, fire, gate, veto, nearmiss, settle). 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?

States a specific verb (read back) and a precisely scoped resource (the trader's last replay of ONE market), then enumerates exactly what is returned: tape beats, strategy trades/state changes, and user moves. It is clearly distinguishable from sibling replay_open, which it names as the prior step.

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?

Gives explicit triggers: 'Use it after replay_open, or when the trader asks what they just watched', and frames the goal as answering from the recording rather than memory. It names the sequencing dependency but does not state when NOT to use it or an alternative read path.

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