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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial non-obvious behavior: an account requirement with a paid tier for depth:"thorough", expected latency of 15-60s (up to ~90s), explicit gaps[] rather than invented answers, contradictions[] on standard/thorough, per-finding hop and citation_uri fields that are only present when actually fetchable, and semantic excerpting instead of head-truncation. That is exactly the kind of context annotations cannot carry.

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?

Long but front-loaded with the highest-stakes information first (account requirement, then the not-signed-in fallback). Nearly every sentence carries routing or behavioral content, though the citation_uri/fetchability sentence is convoluted and the depth explanation repeats the schema, costing some tightness.

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 describing returns and does so concretely: a findings packet with verbatim evidence, confidence, source, fetched_at, stable citations, gaps[], and contradictions[]. Combined with auth, latency, and tier constraints, an agent has everything needed to decide and invoke correctly.

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, including facet counts, hop behavior, and the paid gate. The description's "second-hop iteration" passage largely restates that schema text, adding only the usage implication that multi-step questions resolve in one call. Baseline 3 is appropriate since the schema does the heavy lifting and the description adds marginal value.

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 over 1858 structured sources (SEC, FRED/BLS, FDA, USPTO, markets, etc.) — and explicitly negates the obvious misreading with "this is NOT open-web search." It also names the mechanism (decompose into facets, route to 7,151 tools in parallel) and the return shape, so an agent can distinguish it from ask_pipeworx and from single-lookup siblings 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 routing rules in both directions: use this for broad/multi-part questions over structured data, use ask_pipeworx for a single lookup, and use ask_pipeworx for breaking/colloquial current-news topics because deep_research returns mostly empty gaps[] there. It also states the auth precondition and the fallback when not signed in, and explains which depth setting suits multi-step questions.

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