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

Annotations already declare readOnlyHint=true, but the description adds real value by stating what is deliberately withheld — 'never the keys or endpoint addresses' and 'Provider keys are never returned' — so an agent knows it will not receive secrets. It doesn't cover auth requirements or freshness/caching, so it stops short of a 5.

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 core scope is front-loaded in the opening clause, and the parentheticals each add distinct content (function list, redaction rule, pause semantics) rather than filler. It is a single very dense sentence, which is efficient but slightly harder to scan than a short structured list.

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?

With no output schema and no parameters, the description carries the full burden of describing the response and does so thoroughly — it names every returned field group, including the pause details (who paused, why, affected agents, what resume restores). Nothing an agent needs to interpret the result is missing.

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 baseline of 4 applies; there is nothing for the description to disambiguate. It does not need to compensate for any schema coverage gap since the schema is empty.

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 enumerates exactly what the tool returns — active model provider, which providers have credentials, per-function model assignment, and the autonomy pause state — which is far more specific than a restated name. It also frames itself as the equivalent of `ankra ai status` / `ankra ai autonomy status`, giving an agent an unambiguous mental model of the resource it reads.

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?

Usage is only implied: an agent can infer this reads organisation-level AI configuration, but there is no explicit 'use this when...' statement nor any contrast with close siblings such as get_ai_environment, get_application_ai_config, or list_ai_models. The 'twin of' framing hints at read-only status inspection but doesn't route between alternatives.

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