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

Goes well beyond the readOnly/idempotent annotations: it discloses the full returned shape (dataset_id, datasets[], refresh interval, last refresh, health), enumerates all eight health states, and prescribes behavior for each (refresh once on stale, hand over next_step.url on needs_sign_in, explain reports on reports_missing). It also notes the AUTARIO_API_KEY requirement and that it never handles credentials.

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?

Front-loaded with purpose and the alternative to use, and nearly every sentence is decision-relevant. It is dense and long, and part of the health-state remediation guidance overlaps what refresh_connector and get_connector_status arguably own, but nothing is filler.

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?

There is no output schema, so the description carries the full burden of explaining return values and does so in detail, including the health state machine and per-dataset age. An agent has everything needed to call it and interpret the result.

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 is 4 and there is no schema surface for the description to elaborate on. The description's field-level detail is about the response, not inputs, so it cannot raise this dimension further.

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?

States a specific verb+resource ('List the platform connectors set up on this Autario account') and enumerates the connector categories covered. It is clearly distinguishable from get_connector_status and refresh_connector, which handle per-connector detail and refresh respectively.

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 says to call it 'instead of guessing which ones exist', gives concrete user phrasings that should route here ('my Search Console data', 'my ad spend', 'a cross-platform weekly report'), and states the read-only boundary (connectors are configured in the Autario UI). It also routes follow-up work to query_dataset and get_connector_status.

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