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

Annotations establish readOnlyHint and non-destructive, but the description adds substantial behavior beyond that: live per-worker counters, pooled team/company quotas, UTC-midnight resets, a fingerprint for stale client-side caches, and a service_notices block describing degraded subsystems. It also notes that upgrade_url is empty for company tier, which is non-obvious behavioral information.

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?

Although long, every clause carries decision-relevant detail: quota pooling, reset semantics, stale-cache detection, workflow discovery, and degraded-service notices. The core purpose is front-loaded in the first sentence, and the rest is structured as a compact breakdown of the returned JSON document rather than padding.

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 zero-argument introspection tool with a rich return document, the description fully covers what an agent needs: tier, capabilities, limits, live usage, workflow discovery paths, upgrade_url behavior, and service notices. It also handles edge conditions such as budget pooling per organisation and empty upgrade_url for company tier, so an agent can invoke the tool without lingering ambiguity.

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 parameters, so the schema has nothing to document and the description correctly states that it 'takes no arguments.' Baseline for zero-param tools is 4; no parameter compensation is needed and the description's focus on return semantics is appropriate.

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 clear statement of what the tool returns: 'Tier, capabilities, limits, and live usage for the calling identity.' It goes on to specify the exact shape of the response and explicitly differentiates this capability-introspection call from related sibling tools by naming describe_capabilities for the catalog and list_workflow_types/start_workflow for running workflows.

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 description gives explicit decision-oriented guidance: 'Use this to decide what tools and fan-out paths are available before calling them, or to check remaining quota before issuing more requests.' It also explains the strategic benefit for lower-tier agents—avoiding wasted retries and deciding whether to upgrade mid-conversation—and clearly routes the agent to the follow-up calls that lead to a running workflow.

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