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

Despite annotations already marking readOnlyHint=true and idempotentHint=true, the description adds substantial behavioral context: account requirement, paid tier for depth:'thorough', latency expectations (15-60s, up to ~90s), the gap recovery mechanism, the contradictions[] field, hop field semantics, semantic excerpting behavior, and the guarantee that it 'never invented' data. One possible concern is that the description mentions 'decomposes your question' and 'routes to 5,743 tools' which sounds like stateful orchestration, but the annotations say readOnly and idempotent; the description explicitly describes a non-mutating research operation, so no contradiction.

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-rich but dense and monolithic. It front-loads the account requirement and alternative routing, which is good, but then packs depth mechanics, citation semantics, excerpting behavior, latency, and contradictions into a long multi-clause paragraph. Every sentence earns its place, but the overall structure is hard to parse quickly. A breakdown into a one-line summary plus shorter sections would improve scanability.

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 there is no output schema, the description thoroughly compensates by describing the return shape: findings packet, verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, gaps[], contradictions[], hop field, citation_uri. It covers latency, auth prerequisites, tier differences, and points to the alternative tool. For a complex tool with 2 params and no output schema, this is complete.

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 fully documents both parameters (question and depth). The description adds nuance to the depth parameter by explaining the hop mechanics and paid plan requirement, and gives a natural-language example for the question parameter. That is useful value, but because schema coverage is 100%, a baseline of 3 is appropriate; the extra behavioral color is a bonus, not a necessity.

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 clearly states what the tool does: it performs grounded multi-source research across 1,500 structured data sources, decomposes questions into facets, routes them across 5,743 tools, and returns a findings packet with evidence, confidence, source, and citations. It uses a specific verb ('research'), names the resource domain, and contrasts itself with 'open-web search' and 'ask_pipeworx.' However, it lacks a one-line crisp sibling-differentiating summary statement early on; the differentiation from ask_pipeworx is embedded in a longer paragraph.

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 examples, and explicitly says for single lookups use ask_pipeworx instead. It also tells users without an account to use ask_pipeworx. This is exactly the kind of when/when-not/alternatives guidance that helps an agent select the right tool.

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