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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered, but the description adds that it never starts a run, never changes config, and requires AUTARIO_API_KEY. It also discloses the full return shape (health states, per-dataset data_as_of, reports[], next_step), which is valuable given no output schema exists.

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 purpose and triggering conditions are front-loaded, then the return contract is spelled out. The state enumeration and return-field list make it dense and long, but with no output schema each element carries informational weight rather than repetition.

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 a single low-risk parameter, the description compensates by fully documenting the returned health states, per-dataset semantics, report outcomes, and the next_step action contract. Nothing an agent needs to call and interpret it 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?

There is a single parameter, connector_id, with 100% schema description coverage, so the schema does the heavy lifting (baseline 3). The description only implicitly ties the id to list_connectors output and adds no format or edge-case detail beyond the schema.

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 a specific verb and resource (explain the state of one connected platform) and enumerates the exact facets it reports: freshness, delivered/empty/missing reports, and who must act. It explicitly scopes to a single connector and clarifies it is diagnostic rather than an action tool, distinguishing it from siblings like refresh_connector.

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?

It gives explicit trigger conditions: use when list_connectors shows a non-ok state or before telling the user to sign in again, naming the sibling tool whose output drives the decision. The read-only clause ('never starts a run and never changes the configuration') further routes the agent away from refresh_connector.

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