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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive), and the description adds substantial context beyond them: the paid-tier constraint for depth:'thorough', latency bounds ('15-60s ... up to ~90s'), and output semantics (explicit gaps[] that are 'never invented', contradictions[] for standard/thorough, citations always resolvable). It also discloses the semantic-excerpting behavior that prevents answers deep in long records from being missed. 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?

Dense but well-structured: critical gating facts (account requirement, alternative tool) are front-loaded before mechanism details, and the findings-packet description is tightly enumerated. Minor redundancy — 'use ask_pipeworx instead — it works on every tier' appears twice, once for auth and once for single lookups — keeps it from being perfectly lean.

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 return-value disclosure, and it delivers: findings packet structure (verbatim evidence, confidence, source, fetched_at, citation), gaps[] semantics, contradictions[], hop/citation fields, and excerpting behavior are all specified. Combined with auth, latency, and routing guidance, nothing an agent needs to decide whether and how to call this tool 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%, so the baseline is 3, but the description adds real meaning beyond the schema: it tells the agent what makes a good question (broad/multi-part over structured data, with concrete examples) and attaches a cost/plan constraint to depth:'thorough' that the schema does not state. The depth enum semantics are largely duplicated between schema and description, so the contribution is solidly additive but not transformative.

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, compound operation: grounded multi-source research across Pipeworx's 1,517 structured data sources, decomposing the question into facets and routing them in parallel to 5,798 tools. Explicitly differentiates itself from siblings by asserting 'this is NOT open-web search' and by directing single lookups to ask_pipeworx. Concrete examples ('compare X and Y's regulatory + financial exposure') anchor the intended use.

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?

Explicitly names the alternative and the switching conditions: 'If you are not signed in, use ask_pipeworx instead' and 'For a single lookup use ask_pipeworx.' States when it IS appropriate — 'Best for broad/multi-part questions over structured data' — with two example questions. The description also tells the agent what this tool is not (open-web search), preventing misrouting.

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