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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses real behavioral traits: the data comes from an asynchronous read model, the count is pinned to a freshness checkpoint, coverage starts at a commit-consistent baseline that is not treated as created activity, and archived schedules are counted in their own state. These are exactly the staleness/counting caveats an agent cannot get from annotations or schema.

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 source and scoping constraint are front-loaded and no sentence is pure padding. But the prose is dense jargon — "inventory", "freshness checkpoint", "commit-consistent baseline" — used without definition, and the clause about the baseline not counting as created activity is opaque on first read.

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?

An output schema exists, so return values need not be described, and the temporal/consistency semantics are well covered. The gap is filtering: seven optional parameters with zero documentation anywhere mean an agent cannot know what queueMissing or endpointMissing do or how tier maps to the ClickHouse model, making correct invocation guesswork.

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% across seven parameters, and the description mentions none of tier, state, queueName, endpointId, queueMissing, endpointMissing, or recurrenceKind. The only added meaning is that filters are conjunctive ("can be combined") and the hint that archived is a distinct state — useful, but far short of compensating for a completely undocumented parameter set.

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 names the resource (current schedule inventory) and the source system (asynchronous ClickHouse read model), and explicitly excludes the neighbouring forecast concept ("This is not a future-run forecast"). However, "inventory" is never expanded into what a record actually represents, so the resource stays somewhat abstract compared with siblings like schedules_list or schedules_read.

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?

Only one when-not rule is given (not a forecast), and "Filters can be combined" is the sole usage hint. No alternative sibling is named — schedules_list, schedules_summary, activity_read, and forecast_read all plausibly overlap, yet the description never says which to pick or under what conditions.

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