Jev health, usage and models

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

Annotations already declare readOnlyHint and openWorldHint, so the description's main added value is the cost model: "Free except health/models refresh (one GET)" plus the note that validate is checked offline with "nothing sent." It does not spell out side effects of \"feedback\" or \"calibrate\" (they persist labels/thresholds, and \"reset\" clears counters), which sits in mild tension with readOnlyHint, though these are internal bookkeeping rather than changes to the user's resources.

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 dense opening sentence front-loads the action inventory, followed by the single most decision-relevant caveat about cost. It is compact with no filler, though the parenthetical chain is packed enough that a skim reader may lose the action-to-parameter mapping.

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?

All seven actions are named and briefly defined, the cost/refresh caveat is disclosed, and an output schema exists so return values need not be described. The remaining gap is routing guidance against jev_ask/jev_batch, which the description does not address.

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 100% and every parameter already carries an action-prefixed description, so the schema does the heavy lifting. The description echoes the same action-to-parameter pairings (feedback/label, health/models/refresh) but adds no syntax or format detail beyond what the schema states.

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 opens with a specific scope ("Jev health and housekeeping, no judgments") and then enumerates all seven actions with parenthetical definitions, so an agent can tell what each invocation does. It differentiates itself from jev_ask only obliquely via "validate (offline dry run of a jev_ask input)"; there is no explicit statement that it is the status/introspection counterpart to the query tools.

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 action list implies when each mode applies, and "validate (offline dry run of a jev_ask input)" links it to the ask workflow, but there is no explicit "use this when X, use jev_ask/jev_batch when Y" routing. An agent must infer the split from the sibling names alone.

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