athena_orchestration_replay

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

With no annotations provided, the description must carry the behavioral disclosure burden, but it does not state whether the operation is read-only or has side effects, what prerequisites exist (e.g., run must already exist), or what failure modes look like. It does disclose that verification targets authority snapshot, routing digest, NEXT, GROW, and Pareto state, but the ambiguity of 'Recompile' plus missing side-effect/read-only clarity is a significant gap.

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 entire description is one focused, front-loaded sentence with no filler or repeated schema information. Every phrase adds detail: the action, the scope (one persisted run), the input nature (frozen inputs), and the verification checks.

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, so the description should explain the outcome or return format; it does not. It also omits prerequisites (must the run exist?), side effects, and the meaning of the verified state components (NEXT, GROW). While it names specific verification targets, an agent cannot fully infer what the tool returns or what 'verify' produces, making the description incomplete for reliable invocation.

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 0% and there is a single required parameter run_id. The description adds the semantic context that the run is a 'persisted AORRUN' and that it is recompiled from frozen inputs, which clarifies that run_id identifies such a run. However, it never explicitly names run_id, ties it to the AORRUN identifier, or explains the expected format, so it only partially compensates for the missing schema descriptions.

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 a specific resource ('one persisted AORRUN') and enumerates concrete verification targets (authority snapshot, routing digest, NEXT, GROW, Pareto state). This clearly distinguishes it from sibling tools like athena_orchestration_get/recent, which are retrieval-focused, and from other replay tools that target different resources.

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 'Recompile one persisted AORRUN from frozen inputs' implies the tool is for reproducing/verifying a previously persisted orchestration run. However, it provides no explicit when-to-use or when-not-to-use guidance, and does not mention alternatives among the many orchestration/replay/sibling tools, leaving the selection decision to inference.

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