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

Annotations already declare read-only, non-destructive, and closed-world behavior. The description adds valuable context beyond that: it operates on recorded evidence, performs no new search, and incurs no new charge—key side-effect details an agent needs to know. It does not cover failure modes or what happens if evidence is missing, but the cost and search behavior are well disclosed.

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 short sentences, front-loaded with the core action and followed by the key constraint. Every word earns its place with no redundancy or 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?

For a simple one-parameter replay tool, the description covers the action and cost behavior adequately in context of the read-only annotations. However, it omits any explanation of the required find_id parameter and does not indicate what the replayed checks/decisions look like, leaving a clear gap in parameter semantics.

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 0% for the single required parameter find_id, and the description never mentions or explains it. The agent is left to guess that find_id identifies the run or find whose checks are replayed, with no explicit compensation for the bare schema.

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 uses a specific verb ('Reproduces') and resource ('a run's saved checks') and clarifies the source ('recorded evidence'), making the core action clear. However, it does not explicitly distinguish this from the very similarly named sibling get_find_decisions, which likely retrieves rather than replays decisions.

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 phrase 'No new search and no new charge' implies when to use this tool: to reproduce checks without incurring cost or triggering a fresh search. But it does not explicitly state when to choose this over get_find_decisions or re-running a search, leaving the agent to infer the alternative.

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