Erinys Eval

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

With no annotations, the description carries the full disclosure burden, yet it never says whether evaluation mutates stored memory, how expensive it is to run, or what triggers it. "Self-evaluate" could be read-only or could rewrite scores; the description leaves that ambiguity unresolved.

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?

One short sentence with no filler and no repetition, so it is efficient, but it is efficient by omission rather than by discipline. Nothing is front-loaded beyond the bare action.

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 means return values needn't be described, but the description still omits the parameter meaning, the mutation/cost profile, and how this differs from nearby diagnostics. For a tool in a 28-tool namespace, that leaves too much to inference.

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?

The single optional `project` parameter has 0% schema description coverage and is never mentioned in the description, so the agent has no idea what it scopes or what omitting it means. This is the one parameter that needed compensating text and got none.

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?

"Self-evaluate memory quality" gives a verb and resource, so the action is inferable, but "LOCOMO-inspired metrics" is jargon that doesn't tell an agent what is actually measured or produced. Nothing distinguishes it from sibling diagnostics like erinys_stats or erinys_conflict_check.

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 when-to-use, when-not-to-use, or alternative is named despite 27 siblings including erinys_stats, erinys_conflict_check, and erinys_session_summary that plausibly overlap. The agent must guess whether this is a diagnostic, a scoring pass, or a maintenance step.

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