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

Goes well beyond the readOnly/idempotent/openWorld annotations: discloses the account/paid-plan requirement for thorough depth, the 15-60s runtime (up to ~90s for thorough), that gaps[] are reported rather than invented, that contradictions[] are emitted for standard/thorough, and that large records are semantically excerpted rather than head-truncated. The citation_uri sentence is convoluted and its conditional fetchability caveat is hard to parse, which blunts an otherwise strong disclosure.

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?

Front-loads the two decision-critical facts (account requirement, then the one-call multi-source scope) before elaborating, and nearly every sentence carries operational information. It is dense and somewhat overstuffed — the citation_uri/fetchable-record passage is tangled and revisits ground already implied by "stable pipeworx:// citation per finding".

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?

For a 9-parameter, long-running, paid-tier-gated research tool with no output schema, the description supplies everything an agent needs: preconditions (auth/tier), latency budget, what the findings packet contains (evidence, confidence, source, fetched_at, citation, hop, gaps, contradictions), and how depth changes behavior.

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% with the depth enum fully documented, so baseline is 3; the description adds real meaning on top — that "thorough" requires a paid plan and that standard vs thorough differ in follow-up behavior (gap re-angling vs lead chasing), which affects cost/latency tradeoffs. The seven string aliases for question are left entirely to the schema, and the description says nothing about them.

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 1868 STRUCTURED data sources") plus the mechanism (facet decomposition, parallel routing to 7,194 tools, findings packet). It explicitly negates the nearest wrong reading — "this is NOT open-web search" — and names siblings ask_pipeworx and single-lookup usage, so the agent can discriminate 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 cases ("compare X and Y's regulatory + financial exposure"), explicit when-not cases ("For a single lookup use ask_pipeworx"; breaking/colloquial news topics should go to ask_pipeworx because deep_research returns mostly empty gaps[]). It also routes on tier/auth — "If you are not signed in, use ask_pipeworx instead" — and explains which depth value to pick for multi-step questions.

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