erinys_backfill

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

No annotations are present, so the description bears full responsibility for behavioral disclosure. It mentions 'event-ledger idempotency', which is a useful behavioral trait, but it does not explain the side effects of applying records, whether 'plan' is a dry-run, permission requirements, or any limits. The description is too terse to provide adequate transparency.

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 sentence with no wasted words, and the key verb phrase 'plan or apply' is front-loaded. However, it is so brief that it sacrifices clarity, making it slightly less effective than a perfectly concise but more informative description.

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?

This is a complex tool with five parameters, dual modes, and an idempotency control, yet the description provides only a high-level statement. It does not explain how the plan/apply modes differ, what 'bounded' means, the role of the digest, or how the event-ledger guarantee is realized. The presence of an output schema reduces the need to describe return values, but the overall contextual picture remains incomplete.

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 by explaining parameters. It only loosely connects 'historical records' to the 'items' parameter and 'idempotency' to run_key/digest, but it never defines any parameter semantics. The agent is left to guess the meaning of mode, expected_plan_digest, and repair_temporal_projection.

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 clear verbs 'plan or apply' and identifies the resource as 'bounded historical records', which conveys the tool's core function. It hints at a distinct purpose from sibling save/update tools through the backfill focus, but does not explicitly differentiate itself or define 'bounded', so it falls short of a 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?

The phrase 'historical records' implies a backfill scenario, giving some context for when this tool would be used. However, there is no explicit guidance on when to use this over alternatives like erinys_batch_save or erinys_save, nor any exclusions or prerequisites.

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