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

Despite readOnlyHint=true, idempotentHint=true, openWorldHint=true annotations already covering safety, the description adds substantial behavioral context: auth requirements and tier differences, parallel routing across 5,798 tools, explicit gaps[] never invented, contradictions[] for standard/thorough, semantic excerpting rather than head-truncation, citation_uri resolvability, and expected latency (15-60s, thorough up to ~90s). This is rich, honest behavioral disclosure beyond any annotation.

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 every sentence earns its place: auth gate, alternative routing, scope, architecture, return shape, gaps honesty, depth semantics, latency, and citation reliability. It front-loads the most decisive gate (account required) and the sibling alternative. It loses one point because the depth/behavior semantics are somewhat dense and woven into a long middle block, so quick scanning is harder than it could be with short labeled segments.

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 (2 params, one enum with tier implications, an output contract that the description details thoroughly, and no output schema), the description covers everything an agent needs: prerequisites, pricing/plan boundary, default behavior, latency expectations, response packet characteristics, and fallback routing when the tool cannot be used. No important decision-relevant context 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 description coverage is 100%, so the baseline is already 3, but the description goes beyond the schema by explaining the depth levels in behavioral terms: quick=3 single-hop, standard=3 with gap-recovery and contradictions, thorough=6 paid with iterative lead chasing. It also clarifies that 'standard' is the default (the schema does not state a default), and qualifies the question parameter's broad/multi-part suitability. This genuinely adds meaning an agent needs to choose a correct depth value.

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 states a specific verb (research), a definite resource (Pipeworx's 1517 structured data sources, NOT open-web search), and a clear deliverable (findings packet with verbatim evidence, confidence, source, fetched_at, stable citations, and gaps[]). It explicitly distinguishes itself from sibling tools, including naming ask_pipeworx as the alternative for signed-out users and for single lookups.

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'), gives a concrete example ('compare X and Y's regulatory + financial exposure'), and names alternatives: 'If you are not signed in, use ask_pipeworx instead' and 'For a single lookup use ask_pipeworx.' This is the strongest possible usage guidance in a compact form.

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