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

Annotations already signal read-only, open-world, idempotent behavior, but the description goes far beyond them: it explains parallel facet decomposition, the findings packet format, gaps[] with 'never invented', fetchable citation_uri semantics, contradictions[], semantic excerpting, and expected latency. There is no contradiction with the annotations; the description strengthens what the agent can predict about execution.

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 every sentence largely earns its place given there is no output schema and the tool has complex behavior. It is front-loaded with the critical account requirement and usage alternative. However, a few asides like '(One call, not many)' are slightly ambiguous, and the text is long enough that an agent must parse carefully.

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?

Despite having no output schema, the description fully covers what an agent needs: required authentication, fallback tool, scope of data, output packet shape, citation fetchability, gap behavior, latency expectations, and depth trade-offs. Nothing critical for correct invocation or expectation-setting 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?

Schema coverage is 100%, but the description adds meaning well beyond the schema: it maps each depth value to a concrete number of facets and hop behavior, and clarifies that the question can be broad and multi-part. This gives the agent precise basis for choosing depth and phrasing the question.

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 opens with a concrete, multi-source research purpose: it grounds answers across 1,517 structured data sources and explicitly distinguishes itself from open-web search. It names the sibling ask_pipeworx as the single-lookup alternative, so an agent can tell deep_research apart from other tools without opening schemas.

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 gives explicit when-to-use guidance: it is 'Best for broad/multi-part questions over structured data', and it explicitly says 'For a single lookup use ask_pipeworx instead.' It also provides an account/tier condition ('If you are not signed in, use ask_pipeworx instead'), which is actionable routing information beyond mere sibling differentiation.

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