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

Annotations only cover the safety profile (readOnly/idempotent/openWorld), so the description carries the real behavioral load and does: auth and billing gates, latency budget (15-60s, up to ~90s), what each depth does on a second hop, that gaps[] are declared rather than invented, that contradictions[] are flagged, and the precise caveat that citation_uri is present only when the source emits a resolvable record URI. That is unusually rich context an agent could not infer from the structured fields.

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?

Front-loads the gating fact (account required, fallback to ask_pipeworx) so an agent without auth stops reading immediately, and every clause is informative rather than filler. It is a dense wall of text with some restatement — gaps[], contradictions[] and the citation URI are each explained roughly twice — which costs it the top mark.

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, expensive, multi-hop tool with no output schema, the description still tells the agent what comes back (findings, confidence, source, fetched_at, hop, citation, gaps[], contradictions[]), how long it takes, and when it will degrade to empty results. Nothing material to a correct invocation is left to inference.

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 description coverage is 100%, so the baseline is 3 and the aliases plus the depth enum are already fully documented in the schema. The description still adds value by tying depth to a cost/paywall constraint ("thorough" needs a paid plan) and to iteration semantics (standard = gap recovery, thorough = lead-chasing plus contradiction scan), which is a real decision input beyond the enum text.

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 1,879 structured data sources, decomposed into facets and routed to 7,146 tools in parallel — and returns a named artifact (findings packet with evidence, confidence, source, citation, gaps[]). It explicitly negates the nearest misreading ("this is NOT open-web search") and distinguishes itself from ask_pipeworx, so an agent can route between them 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 use-cases ("compare X and Y's regulatory + financial exposure"), a concrete example question, and two explicit exclusions with the alternative named: single lookup → ask_pipeworx, breaking/colloquial news → ask_pipeworx (with the reason: mostly empty gaps[] outside the structured catalog). It also states the precondition (free account; paid plan for thorough) and which tool works if not signed in.

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