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

With no annotations provided, the description carries full behavioral burden. It adds valuable context: 'Always small' signals response size expectations, 'call this first' establishes workflow ordering, and listing the returned content clarifies the tool is a read-only summary. While it does not explicitly state side effects (none are expected for a summary), the description provides enough behavioral context beyond a bare listing.

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 with zero filler. The core purpose ('Compact replay summary') is front-loaded, followed by a tight list of return contents and a clear usage directive. Every word earns its place.

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?

Although there is no output schema, the description sufficiently enumerates the response shape (metadata counts + per-step rows with named fields) and gives workflow context. An agent has everything needed to invoke the tool correctly and interpret its result for a summary.

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%, and the single required parameter replayId is already described as 'Replay ID.' The description adds no additional semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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 ('returns') and resource ('replay summary'), then enumerates the exact fields (totals, passed/failed/skipped counts, per-step status, action, duration, diff scores, error excerpt). This clearly distinguishes it from sibling flow_replay_step, and an agent can identify the tool's purpose at a glance.

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?

Explicitly instructs to 'call this first when analyzing a replay' and names the alternative 'use flow_replay_step for full per-step detail.' This is unambiguous guidance on when to use this tool versus its closest sibling, with no inference required.

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