athena_gap_replay

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

No annotations are provided, so the description carries the full burden. It does not disclose whether this operation is read-only, has side effects, requires permissions, or what the output format is. The phrase 'frozen inputs' hints at a non-mutating replay, but this is not explicitly stated.

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 that front-loads the primary verb and resource. No wasted words; all elements support the core function.

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?

The tool has no output schema and no annotations, and the description uses domain-specific jargon without explanation. It leaves open critical questions: what a GAPRUN is, what frozen inputs are, what the four comparison outputs mean, and how the output is presented. This is insufficient for a non-expert agent.

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?

With 0% schema description coverage, the description must compensate, but it only indirectly references the parameter via 'one GAPRUN'. It does not explain how to obtain a run_id, what valid values look like, or the format expected. The link between run_id and GAPRUN is minimal.

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 'recompile' and identifies the resource 'GAPRUN', and states the comparison of specific outputs (closure nodes, gap, grow, decision digest). However, it doesn't explicitly distinguish this from other replay tools in the family (e.g., athena_field_replay, athena_cycle_replay), and terms like 'GAPRUN' and 'closure nodes' are unexplained, so it's not fully clear to an unfamiliar agent.

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?

There is no explicit guidance on when to use this tool vs alternatives. It doesn't mention any sibling tools or exclusions. The usage is only implied by the verb 'replay', but no context is given about prerequisites or situations requiring this tool.

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