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

Annotations already say readOnly/openWorld/idempotent/not-destructive, and the description adds substantial beyond-annotation context: account/paywall requirements, parallel facet routing, findings-packet shape with verbatim evidence + confidence + source + fetched_at + stable pipeworx:// citation, explicit gaps[] for unanswered facets (never invented), contradictions[] for standard/thorough, semantic excerpting of large records, and expected latency (15-60s, up to ~90s). It also explains the citation is always fetchable. No contradiction with annotations.

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 nearly every sentence carries new behavioral information: auth, alternative routing, source scope, mechanism, output packet fields, honesty guarantees, depth tiers, latency. The critical routing facts (account requirement, alternative tool) are front-loaded in the first sentence. It is dense rather than padded; slight redundancy in listing data sources twice (1,517 sources and 5,798 tools) and the parentheses-heavy style prevent a 5.

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?

Given the tool's complexity (2 params, no output schema, no nested objects), the description is remarkably complete: it explains scope, auth, alternatives, return-value shape, latency, depth semantics, failure behavior (gaps[], never invented), contradictions[], and record excerpting. There is no output schema to lean on, so the description carries the full burden and succeeds. An agent has everything needed to invoke it correctly and interpret results.

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% and the schema already documents both parameters, with the depth enum fully spelled out. The description adds value beyond the schema by explaining the meaning of depth levels in behavioral terms ('quick=3 single hop', 'standard adds a gap-recovery hop + contradictions[] scan', 'thorough=6 paid adds a full iterative hop') and by explaining what kind of question to put in `question` ('Broad/multi-part is fine — decomposition is the point'). Baseline is 3 due to full schema coverage; the added semantic depth pushes it to 4.

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 states a specific, rich task — grounded multi-source research across 1,517 structured data sources in one call — with a concrete mechanism (decomposition into facets, parallel routing to 5,798 tools), an explicit negative scope ('this is NOT open-web search'), and a usage example. It distinguishes itself from ask_pipeworx and open-web search, so an agent can tell it apart from siblings like ask_pipeworx, bet_research, and compare_entities 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?

Gives explicit when-to-use ('Best for broad/multi-part questions over structured data') and explicit when-not-to/alternative ('If you are not signed in, use ask_pipeworx instead... For a single lookup use ask_pipeworx'). It also names the alternative tool and the condition that selects it, and the paid-tier caveat is stated up front. This is exactly the routing guidance an agent needs.

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