Deep multi-angle analysis from verified data

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

The description goes well beyond the sparse annotations: it explains execution in the sandbox, verification badges, cross-agency series joining, slower latency (60-180 seconds), error responses, and API key requirements. There is no contradiction with `readOnlyHint: false`.

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?

Every sentence earns its place: core behavior, output characteristics, error behavior, routing guidance, and auth requirements. The description is dense but well-structured and front-loads what the tool is before diving into operational constraints.

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?

For a complex tool with no output schema, the description covers what matters: the report nature, verification, the sandbox execution model, latency, error cases, and authentication. An agent has enough information to select, invoke, and interpret the result of this 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?

Schema coverage is 75%, so the description still carries some parameter burden. It clarifies the `question` parameter through example phrasings and explains `series` behavior via cross-agency joining and plan-width limits. It does not add detail on `start`/`end` defaults, but the schema already documents their format.

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 capability: a planned multi-section report with 3-4 orthogonal analyses computed via real Python in the sandbox over verified data. It also distinguishes itself from the `answer` sibling by latency and use-case phrasing, so an agent can tell which tool fits.

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 phrases ('analyze', 'break down', 'give me a full picture') and explicitly says to use `answer` for a single direct question. It also discloses the series_limit error for exceeding plan width and the key_required error for missing auth, giving clear routing and failure guidance.

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