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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, so the safety profile is covered. The description goes well beyond that by disclosing concrete runtime behavior: parallel decomposition across tools, findings packet shape, verbatim evidence plus confidence/source/fetched_at, stable pipeworx:// citations, gaps[] for unanswered facets, contradictions[] for standard/thorough, hop fields, semantically excerpted large records, and a 15-90s latency expectation. It also explicitly says findings are 'never invented', which is important trust context for an AI agent.

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 information-dense and packs many valuable behavioral details, but it is long and somewhat meandering, with parentheticals and back-to-back clauses that make parsing harder than necessary. The opening account/sign-in notice is important, but the structure front-loads eligibility before stating what the tool does, so the core purpose arrives late. Every sentence earns its place, but the organization could be tighter.

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?

Given the tool's complexity (parallel multi-tool routing, three depth levels, gaps/contradictions semantics, citation fetchability, latency), the description provides essentially everything an agent needs to invoke it correctly: selection criteria, account tiers, depth semantics, return-packet contents, gap/contradiction behavior, and latency expectations. No output schema exists, so the description must explain return values, and it does so in detail.

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 input schema already documents both question and depth semantics in detail. The description restates the depth values and adds the paid-plan constraint for thorough and the hop/contradiction behavior per depth, which usefully supplements the schema but does not need to carry much additional weight because the schema is already thorough. Baseline 3 is appropriate.

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?

The description opens with a concrete verb plus resource ('Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call') and immediately differentiates itself from open-web search and from ask_pipeworx. It names exact example questions and states the intended niche (broad/multi-part questions over structured data), so an agent can reliably distinguish this from siblings such as ask_pipeworx, compare_entities, and entity_profile.

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?

The description gives explicit when-to-use guidance: 'Best for broad/multi-part questions over structured data', and it provides a concrete when-not-to-use rule: for breaking/current news use ask_pipeworx, since deep_research returns mostly empty gaps[]. It also states the account requirement and the paid-tier constraint for 'thorough'. These are explicit selection criteria rather than implied context.

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