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

The description discloses that the tool 'consumes AI credits'—a key behavioral trait not captured by the annotations (all false). It also explains the asynchronous behavior (returns inline or job_id for polling), adding useful operational context. With annotations that are neutral and uninformative, the description carries the burden and does so well, though it doesn't mention failure modes or rate limits.

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 description is concise and well-structured: the first sentence states the core purpose, the second explains the return behavior, and the third provides actionable prerequisite guidance. Every sentence earns its place with no redundant filler, and important details are front-loaded.

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 an output schema available (so return values are documented), the description covers the essential context: the core action, the async return modes, and the data-source prerequisite with alternative ingestion paths. It doesn't mention error scenarios or credit limits, but those are secondary given the clear guidance provided.

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 input schema has 100% coverage, with detailed descriptions for `question`, `wait_seconds`, and `session_id`. The tool description doesn't add parameter-specific meaning beyond the schema, so the baseline of 3 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 uses a specific verb ('run') and resource ('natural-language analytics question against your connected data sources'), making the tool's purpose immediately clear. It also distinguishes the tool from siblings by describing the two possible return modes (inline result or job_id for polling), which sets it apart from tools like get_analysis_status or list_data_sources.

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 explicitly states when NOT to use the tool: if list_data_sources returns an empty list, the agent should first ingest data using named alternatives (upload_data_source, ingest_url_data_source, or request_oauth_integration_url). It also references get_analysis_status for polling, giving clear workflow guidance and alternative paths.

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