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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial behavior beyond that: latency expectations (15-60s, up to ~90s for thorough), a guarantee that citations are always fetchable ('present only when the source emits one that resources/read can actually serve'), the gaps[] 'never invented' policy, contradictions[] scanning at standard/thorough, and semantic excerpting rather than head-truncation. This is exactly the kind of behavioral texture an agent needs.

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 long, but every sentence earns its place: account gate, structured-data scope, decomposition behavior, output packet contents, gaps policy, best-for + alternative, depth iteration semantics, citation guarantee, contradictions, excerpting, timing. Dense but front-loaded with the most critical constraint (account required). Slightly over-loaded as one block, but appropriate for a tool this complex.

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 carries the full burden of explaining return values — and it does: findings packet (verbatim evidence + confidence + source + fetched_at + citation), gaps[], contradictions[], hop field, semantic excerpting. It also covers prerequisites, failure/limitation behavior (never invented), alternatives, and timing. Nothing an agent needs to invoke and interpret this correctly 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% and the schema already documents depth levels in detail, so baseline is 3. The description adds value beyond the schema by tying depth to the paid tier ('depth:"thorough" needs a paid plan'), to latency, and to the iteration hop count — information the schema enum does not carry. It does not repeat param syntax, which is fine, but it could not add much more.

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 and resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call'. Explicitly distinguishes itself from open-web search ('this is NOT open-web search') and from the sibling ask_pipeworx ('For a single lookup use ask_pipeworx instead'), so an agent can tell them apart without inspecting either schema.

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?

Gives explicit when-to-use guidance ('Best for broad/multi-part questions over structured data' with concrete example prompts), names the alternative for the wrong case ('For a single lookup use ask_pipeworx instead'), and adds a precondition ('If you are not signed in, use ask_pipeworx'). Nothing is left to inference.

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