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

Beyond the readOnly/destructive annotations, it discloses the parallel decomposition behavior, the findings-packet format (verbatim evidence, confidence, source, fetched_at, citation_uri), the gaps[] honesty guarantee, contradictions[] at standard/thorough, excerpting behavior for large records, hop field, latency expectations, and the account/depth gating. This is rich operational disclosure well beyond structured annotations.

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?

Dense but not bloated. The opening account gating is important and front-loaded. Some examples and parentheticals make it longer than ideal, but every sentence carries operational information; the length is justified by the tool's complexity.

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 only two parameters and rich annotations, the description covers account prerequisites, routing behavior, return format, failure honesty, citation resolvability, latency, and depth semantics. It also positions itself among siblings (ask_pipeworx). Nothing an agent needs to decide whether to call it or set `depth` 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 the schema already documents both parameters thoroughly. The description adds value by mapping depth levels to hop counts and behaviors ('quick=3', 'standard adds gap-recovery hop', 'thorough adds iterative hop + paid'), going beyond the schema's enum text. Minor gap: it doesn't reiterate that `question` accepts natural language, but the schema already covers that.

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 names a specific verb ('researches'), an exact resource ('Pipeworx's 1506 structured data sources'), and a distinctive mechanism (facets routed in parallel across 5,767 tools). It explicitly differentiates from open-web search and names ask_pipeworx as the alternative for single lookups, so an agent can tell this from its siblings immediately.

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 states when to use it ('broad/multi-part questions over structured data', with concrete examples) and when not to ('BREAKING or colloquial current-news topics, use ask_pipeworx instead'; 'single lookup use ask_pipeworx'). It also gives account-tier requirements and a fallback ('If you are not signed in, use ask_pipeworx instead').

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