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

Annotations already declare readOnly, idempotent, and non-destructive; the description adds valuable behavioral context beyond that: it explicitly guarantees 'Secrets and credentials are never included', and it discloses that results differ for authenticated vs. unauthenticated callers (public manifest vs. personal reality). This is critical for an agent deciding whether to use the tool and how to interpret the response.

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 dense but well-organized, front-loading the purpose ('data map... query app-first') before detailing the return payload and usage triggers. Every sentence contributes value, though the length and single-paragraph structure could be slightly tightened with bullet points. It remains focused and free of fluff.

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, the description must inform the agent of what to expect, and it does: manifest components, connector-instance table details (column list, row count, dataset_id, last refresh), saved artifacts, and ready-to-run query examples. It also covers authentication differences and the exclusion of secrets. Minor omissions like error handling or pagination do not significantly weaken completeness for a read-only tool.

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 already provides 100% coverage for both parameters, so the baseline is 3. The description adds only one useful semantic nugget: 'app ids come from list_apps', which helps the agent source the required app_id. It does not elaborate on the format parameter, but that is already self-explanatory in 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 clearly states a specific verb (query) and resource (app context), and explicitly differentiates it from related tools by framing it as 'the data map behind ONE autario app' vs. querying individual datasets. It also lists concrete connector providers and distinguishes authenticated vs. unauthenticated views, making the tool's purpose unambiguous.

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 provides explicit when-to-use triggers with example user queries ('what does my <app> run on', 'query my Search Console data') and tells the agent that app ids come from list_apps, the natural prerequisite. It also references query_dataset and the REST endpoint as follow-ups, guiding the agent on how to consume the returned dataset IDs.

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