Erinys Prune

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

With no annotations, the description carries the full burden, yet it never states that pruning removes data permanently, whether it is reversible, what permissions are required, or whether it touches related records. 'Decayed' hints at a decay-score heuristic, but the destruction semantics of a mutation tool remain undisclosed.

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?

It is a single front-loaded sentence with no filler, but the brevity comes at the cost of under-specification rather than efficiency. Space exists for the destructive/dry-run distinction that was left out.

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 output schema covers return values, so that is not a gap. However, for a data-destroying tool with zero annotations and zero schema descriptions across two parameters, the definition omits reversibility, scope of deletion, and the dry_run safety default — an agent cannot safely invoke it on the text alone.

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%, so the description must compensate. 'Below threshold' clarifies what the threshold value controls, but the dry_run parameter — the most safety-relevant one, defaulting to true — is never mentioned in the description, leaving the simulate-vs-execute behavior unexplained.

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 gives a specific verb ('prune') and resource ('decayed observations') plus a selection condition ('below threshold'), so the agent knows it is a threshold-driven cleanup rather than a general delete. It does not distinguish itself from close siblings such as erinys_delete or erinys_forget, leaving the prune-vs-delete distinction to inference.

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?

No guidance on when to run this versus erinys_delete, erinys_forget, or erinys_supersede, and no prerequisites or preconditions are stated. The agent must guess the intended workflow context entirely.

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