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

Annotations already cover the safety profile (readOnly, non-destructive, not open-world), and the description adds substantial behaviour beyond them: counters reset at UTC midnight, Redis-backed quota/concurrency shared across workers and replicas so adding workers does not multiply allowance, in-memory counters in Redis-less development, per-org pooled budgets, and null-with-unavailable_reason rather than zero on failed document reads. These are non-obvious operational traits an agent cannot infer from annotations.

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?

Purpose is front-loaded, but the body is a single dense run-on paragraph that enumerates nearly every return field (tier, capabilities, limits, workflow_run_search_allowance, usage_today, documents, tool_surface, workflow_discovery, upgrade_url, service_notices) plus ADR citations, much of which duplicates the output schema that already exists. Many clauses do not need to be in the description to call this zero-argument read tool.

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?

For a no-argument, read-only tool with an output schema, nothing needed to invoke it correctly is missing: audience (visible to all tiers), argument behaviour, quota/reset semantics and degraded-subsystem signalling are all covered. Completeness is in fact beyond what the task requires.

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 tool takes zero arguments, so the baseline is 4, and the description reinforces this with 'takes no arguments' and 'visible to all tiers'. There is no parameter surface left to explain.

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?

Opens with a concrete noun phrase naming exactly what is returned: tier, capabilities, limits and live usage for the calling identity. It also disambiguates against siblings by naming describe_capabilities, list_workflow_types and start_workflow in the workflow-discovery section, so an agent can position this tool against neighbours without opening a schema.

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?

Explicitly states when to reach for it: before calling tools or fan-out paths, and before issuing more requests to check remaining quota, with a motivating scenario (lower-tier agents avoiding wasted retries or upgrading mid-conversation). No explicit when-not-to-use or direct statement that describe_capabilities is the alternative for the catalog view, which keeps it short of a 5.

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