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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds substantial behavioral context beyond annotations: the 15-60s latency (up to ~90s for thorough), the explicit gaps[] for unanswered facets, the semantic excerpting behavior, the fetchable citation_uri guarantee, and the contradictions[] scan. It also discloses that open-web topics are not covered. This is strong behavioral disclosure, though it doesn't mention rate limits or concurrency limits.

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 front-loaded with the account requirement and the key alternative, but it is quite long and somewhat stream-of-consciousness, mixing multiple topics (account tiers, gap recovery, citations, latency) without clear paragraph or bullet structure. Every sentence carries information, but the wall-of-text format makes it harder for an agent to parse. It earns a 3 for being thorough yet structurally dense.

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 complex research tool with two parameters and no output schema, the description is remarkably complete. It explains return format (findings packet with verbatim evidence, confidence, source, fetched_at, citation_uri), failure behavior (gaps[] never invented), depth semantics, latency expectations, and auth prerequisites. It even explains how large records are excerpted. The only missing piece is explicit statement about what the output JSON looks like, but there's no output schema and the detailed description compensates.

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 schema already documents both parameters well. The description enriches the depth parameter by explaining the behavioral difference between quick/standard/thorough in terms of hops, gap recovery, and contradiction scanning, which goes beyond the schema's enum descriptions. It also clarifies what 'question' should look like via the broad/multi-part guidance and examples. This adds meaningful value above the schema.

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 precisely states the tool's function: grounded multi-source research across Pipeworx's 1500 structured data sources in one call, with decomposition into facets and parallel routing. It clearly differentiates from open-web search and names sibling alternatives like ask_pipeworx for single lookups. The examples of broad/multi-part questions further anchor what the tool is for.

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 directly says 'For a single lookup use ask_pipeworx instead.' It also provides an exclusion for live/news topics, recommending ask_pipeworx for those. The account-required condition and depth-tier differences are clearly stated, leaving no ambiguity about when this tool is appropriate.

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