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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses substantial behavior: it decomposes questions, routes to 5,743 tools in parallel, returns a findings packet with verbatim evidence/confidence/source/fetched_at/citations, uses explicit gaps[] and never invents answers, performs gap-recovery hops, detects contradictions, and semantically excerpts long records. Latency expectations (15-60s, up to ~90s) are also provided. This is far richer than what annotations alone convey.

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 densely packed with essential operational facts: auth, pricing, alternatives, taxonomy of depths, output format, citation reliability, contradiction handling, and latency. It is front-loaded with the account requirement. Some repetition exists (paid plan for thorough appears both at the start and in the depth explanation), so it isn't maximally concise, but the complexity of the tool justifies most of the length.

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?

There is no output schema, and the description fully compensates by explaining the return format: findings packet, per-finding fields, gaps[], contradictions[], hop field, and citation_uri conditions. It also covers authentication, plan tiers, sibling fallback routes, and timing expectations. For a complex research tool with only two parameters, the description leaves no critical gap in an agent's ability to call it correctly.

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 baseline is 3; the description adds meaningful value on top of the schema. It elaborates depth semantics (quick=3 facets, standard adds gap-recovery + contradictions, thorough adds iterative lead-chasing), notes the paid requirement for thorough, and gives examples of appropriate questions. This goes beyond simply restating the enum descriptions.

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 identifies the tool as 'grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources' in 'ONE call', which is a specific verb, resource, and scope. It distinguishes itself from ask_pipeworx and open-web search, and includes concrete example questions. This makes the tool's purpose unmistakable even among many siblings.

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 guidance on when to use this tool versus ask_pipeworx: 'Best for broad/multi-part questions over structured data' and 'For a single lookup use ask_pipeworx'. It also specifically excludes breaking/current-news topics, noting that deep_research 'returns mostly empty gaps[]' in those cases while ask_pipeworx routes to live news APIs. Account and paid-tier requirements are stated up front, covering prerequisites as well.

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