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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, so the description doesn't contradict them. It adds substantial behavioral context beyond annotations: account/signup requirements, parallel decomposition, verbatim evidence with gaps[] never-invented guarantee, citation resolution semantics, contradictions[], semantic excerpting, and latency expectations. This is model-rich disclosure of how the tool behaves.

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 includes valuable content, but it is long and meandering — the first sentence packs account requirements and a URL into the main behavioral description, and the 'ever-invented' quirk is embedded in a parenthesis-heavy sentence. It earns its content but could be better organized with clear sections or bullet-like separation.

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 2-parameter read-only tool with full schema coverage and rich sibling context, the description is nearly complete. It covers when to use, expected latency, depth behaviors, output shape (findings packet, gaps, contradictions, citation_uri), and preconditions. No output schema, so the description carries the burden of return semantics — which it handles thoroughly. Minor gap: it doesn't define `hop` field meaning, but the overall context is sufficient.

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. The description still adds meaningful behavioral nuance beyond the schema: depth values map to facets/hops (quick=3 single hop, standard=3 plus recovery hop, thorough=6 paid), and it clarifies multi-part questions are acceptable. The description doesn't add format-level detail for question, but it does enrich depth semantics.

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'), resource ('Pipeworx's structured data sources'), and differentiates from open-web search and from sibling ask_pipeworx. It explicitly names what the tool is NOT (not open-web search) and mentions the alternative for signed-in/single-lookup cases, so an agent can distinguish it from 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 explicitly says when to use this tool: broad/multi-part questions over structured data ('compare X and Y's regulatory + financial exposure'), and when NOT to use it: if not signed in use ask_pipeworx, for a single lookup use ask_pipeworx. It also covers depth-level tradeoffs and expected latency.

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