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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the 'when available' conditionality (results may be absent) and the scope limitation that it is not predictive, neither of which appears in the annotations.

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?

Three sentences with the return value front-loaded, followed by scope constraints. It is tight overall, but the third sentence partially restates the 'historical policy replay only' limitation, a minor redundancy that keeps it just below 5.

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?

For a zero-input getter with an output schema, the description covers what is returned and the key usage constraint so an agent can call it correctly. It does not address what the response looks like when the summary is unavailable, a small gap against full completeness.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. The schema's own description confirms 'No inputs,' and there is no parameter surface for the description to explain further.

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 and resource: it 'Returns a saved Control > Backtest policy replay summary... plus the policy snapshot used for context.' That is clear and distinguishable from generic siblings like get_policy, though it does not explicitly name or contrast with an alternative sibling, which keeps it at 4 rather than 5.

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?

It gives an explicit positive scope ('Use for historical policy replay questions only') and a negative scope ('Does not predict future performance or recommend policy settings'). That is clear when/when-not guidance, but it stops short of naming the alternative tool an agent should reach for instead, so it falls short of a 5.

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