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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false; the description adds substantial behavioral context on top: account/auth requirements, parallel decomposition into facets, findings packet shape, gaps[] for unanswered facets, contradictions[] scans, 'never invented' honesty, resolvable citation_uri conditionality, semantic excerpting, and expected latency ranges. This goes far beyond what annotations provide and never contradicts them.

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 description is long but dense, with critical constraints front-loaded (account requirement and alternatives) followed by capability, use cases, depth semantics, citation guarantee, and timing. Every sentence adds operational value; minor redundancy exists because the depth parameter behaviour is described both in prose and in the schema enum, so a small deduction for repetition.

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?

The tool has high complexity (3 depth modes, parallel routing, gaps, contradictions, hop fields, citations) and no output schema, yet the description explains the full return envelope, auth boundaries, tier restrictions, latency expectations, and when results may be empty. Sibling coverage routes the agent to the right alternatives. Nothing an agent needs to call this correctly 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 baseline is 3, and the description adds meaning beyond the schema: it explains the behavioral effect of each depth value ('standard' re-angles unanswered gaps, 'thorough' chases leads), ties depth to response time and contradiction scans, and clarifies that broad questions are welcome. The prose depth explanation slightly duplicates the schema enum descriptions, but the added usage context justifies a 4.

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 1500 STRUCTURED data sources ... in ONE call', with concrete examples ('compare X and Y's regulatory + financial exposure'). It explicitly distinguishes itself from open-web search and from ask_pipeworx, so an agent can tell it apart from siblings without opening schemas.

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 guidance: 'Best for broad/multi-part questions over structured data', and explicit exclusions: 'For a single lookup use ask_pipeworx' and 'For BREAKING or colloquial CURRENT-NEWS ... prefer ask_pipeworx'. It also names alternatives and explains why deep_research would fail on those cases, leaving no selection ambiguity.

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