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

Annotations only mark the tool read-only/idempotent/open-world, and the description adds substantial behavior beyond that: parallel facet routing, the findings-packet shape (verbatim evidence + confidence + source + fetched_at + stable pipeworx:// citation), the never-invented gaps[] policy, contradictions[], latency (15-60s, ~90s for thorough), and semantic excerpting rather than head-truncation. 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?

Far beyond appropriate size: depth-tier semantics are explained three times (in the schema, early in the description, and again inside the long embedded note), with nested parentheticals, run-on sentences, and a garbled truncated tail ('i2 (Note: if you ask a quick follow-up ... also strong') that ends mid-thought. Critical info is front-loaded, but the second half is repetitive and unstructured.

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 return-value burden and discharges it: findings packet, gaps[], contradictions[], citation fetchability, latency, and auth/paywall constraints are all covered. The only deductions are the truncated trailing section and no mention of rate or cost limits — minor for a no-output-schema tool of this complexity.

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, and the description adds meaning beyond it: question-framing guidance (opinionated/analytical questions are a better research fit) and depth consequences ('quick/standard show the top-3 most relevant documents per facet; thorough 6'). It does not need to re-document either parameter.

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 Pipeworx's 1517 STRUCTURED data sources ... in ONE call', and explicitly disambiguates with 'this is NOT open-web search'. Distinguishes from siblings by naming ask_pipeworx and by giving concrete example queries ('compare X and Y's regulatory + financial exposure').

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/when-not rules with named alternatives and rationale: 'if you are not signed in, use ask_pipeworx', 'For a single lookup use ask_pipeworx', and recency-framed or concrete-noun-plus-quantity queries favor ask_pipeworx because 'decomposition can miss recency'. Also advises depth-tier selection ('standard' for a first draft, 'thorough' for final), so an agent is never left to guess.

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