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

Annotations only declare readOnly/openWorld/idempotent/non-destructive; the description adds far more: an auth gate with a signup URL, tier-dependent depth, expected latency (15–60s, ~90s for thorough), what the findings packet contains (verbatim evidence, confidence, source, fetched_at, pipeworx:// citation), gaps[] behavior for unanswerable facets, contradictions[] on standard/thorough, citation_uri fetchability, and semantic excerpting instead of truncation.

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 critical constraints (account required, paid tier for thorough) are correctly front-loaded, but the body is a single dense block with repetition — ask_pipeworx routing is stated three times and the 'not open-web search' point is restated. It is information-rich but longer than it needs to be.

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 return values and does so (findings packet fields, gaps[], contradictions[], hop, citation_uri). Combined with auth, latency, and failure-mode disclosure, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description goes beyond it by explaining what each depth actually does behaviorally: standard re-angles unanswered gaps, thorough chases first-pass leads plus gap recovery, and both add a contradiction scan. It also clarifies that the question can be broad/multi-part and that aliases are accepted.

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+resource: decomposes a question into facets, routes each in parallel to tools over 1,870 structured sources, and returns a findings packet. It explicitly excludes open-web search and names the sibling (ask_pipeworx) it is not, so an agent can distinguish it without opening any 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 examples ('compare X and Y's regulatory + financial exposure'), when-not rules (single lookup → ask_pipeworx; breaking/colloquial news → ask_pipeworx because live news APIs are elsewhere), and a prerequisite (sign-in required, paid plan for depth:"thorough"). Depth levels are tied to concrete question shapes.

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