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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, but the description adds substantial context beyond them: authentication and tier gating, latency expectations (15–60s, up to ~90s for thorough), the guarantees of the findings packet (verbatim evidence, confidence, source, fetched_at, never-invented gaps[]), contradiction flagging, semantic excerpting rather than head-truncation, and the caveat that citation_uri only appears when the source emits a resolvable record. The only reason this is not a 5 is that the redundancy around contradictions and citations makes some of the disclosure restated rather than new.

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 most decision-critical item — account required and the ask_pipeworx fallback — is front-loaded, followed by purpose, exclusions, then mechanism. Every paragraph carries usable information, but the text is dense and repeats the contradictions[] guarantee (once in the depth discussion, once near the end) and the citation fetchability claim, which could be consolidated.

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?

There is no output schema, so the description properly takes on the burden of describing the return shape — findings packet fields, gaps[], contradictions[], hop, citation_uri — plus latency and auth requirements. For a tool this complex, nothing an agent needs in order to decide, authenticate, and interpret results 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 depth enum is already fully documented in the schema, so the baseline is 3. The description does add value by framing what each depth level means in operational terms — hop counts, gap recovery vs. lead-chasing, and which levels trigger contradictions[] — which helps an agent pick a depth deliberately rather than guessing. The eight question aliases are left entirely to the schema, which is fine given full coverage.

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 1,867 structured data sources — and explicitly carves out what it is not ("this is NOT open-web search"). It also describes the mechanism (facet decomposition, parallel routing across 7,190 tools) and the output packet, so an agent can distinguish it from ask_pipeworx without opening a 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 (broad/multi-part questions over structured data, with two concrete example phrasings), explicit when-not-to-use (single lookup → ask_pipeworx; breaking or colloquial current-news → ask_pipeworx, with the reason: empty gaps[]), and tier prerequisites (free account, paid for depth:thorough). Alternatives are named with the selecting condition, not left to inference.

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