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

Well beyond the readOnly/openWorld/idempotent annotations, the description discloses auth requirements (free sign-in; thorough needs paid plan), latency (15-60s, up to ~90s for thorough), return packet structure (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), the never-invents guarantee on gaps[], contradictions[] on standard/thorough, hop semantics, guaranteed-resolvable citation_uri, and semantic excerpting behavior. No contradiction with annotations — openWorldHint is consistent with live structured sources even though it is not web search.

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?

Long (~230 words) but every sentence earns its place for a tool of this complexity — front-loaded with the most critical operational constraint (account required + fallback) before the generative details. Minor redundancy exists where depth-mode behavior overlaps with the schema's depth description, but the length is justified by the wealth of non-obvious behavioral detail.

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?

With no output schema, the description carries the full burden of explaining return values — and it does: findings packet, gaps[], contradictions[], hop field, citation_uri resolvability, and excerpting behavior. It also covers prerequisites (sign-in), edge cases (empty gaps for unsupported topics), latency, and the when-not-to-use path. For a 2-param tool with subtle failure modes, nothing an agent needs to invoke it correctly 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%, giving a baseline of 3 since the schema already documents both parameters. The description adds genuine value beyond the schema: it clarifies what makes a good question (broad/multi-part over structured data) and what yields empty gaps (news/colloquial topics), and it explains the practical behavioral difference between depth values (gap-recovery hop, lead-chasing, contradiction scan). This exceeds the baseline.

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?

States a specific verb and resource: 'Grounded multi-source research across Pipeworx's 1569 STRUCTURED data sources... in ONE call.' It explicitly disambiguates from siblings with 'this is NOT open-web search' and does not merely restate the title 'Deep Research.' An agent can tell exactly what this tool does and how it differs from the 38 sibling tools.

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?

Provides explicit when/when-not/alternative guidance: 'Best for broad/multi-part questions over structured data,' 'For a single lookup use ask_pipeworx (one LLM call, not many),' and 'For BREAKING or colloquial CURRENT-NEWS... prefer ask_pipeworx.' It even names the auth-based fallback ('If you are not signed in, use ask_pipeworx instead') and gives worked example questions. Nothing is left to inference.

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