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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, and the description is consistent with these — no contradiction. Beyond the annotations it discloses operational behaviors that matter for invocation: the account/paid-tier requirement, latency expectations ('15-60s', 'thorough ... up to ~90s'), the gap-recovery and contradictions[] passes, the guarantee that citations are only returned when fetchable ('a citation you get back is always fetchable'), and the semantic-excerpting behavior for large records. This is exactly the contextual burden descriptions should carry when they add value beyond structured fields.

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 information-dense, and it is front-loaded with the most decision-critical facts: account requirement and the fallback tool appear in the first clause. Almost every sentence earns its place (runtime, output shape, exclusions, citation semantics, gap handling). It loses one point for being a single wall-of-text paragraph that partially duplicates the schema's depth-enum descriptions.

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 correctly carries the burden of explaining return values — and it does so thoroughly: findings packet contents, gaps[], contradictions[], hop field, and citation_uri presence conditions. It covers prerequisites, latency, alternatives, and the structured-vs-open-web boundary. For a 2-parameter, 30-sibling, no-output-schema tool, an agent has everything needed to select and invoke 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 description coverage is 100%, so the baseline is 3: the schema already documents question and the depth enum in detail, including facet counts, hops, and the paid flag. The description's depth discussion largely restates the schema ('standard ... re-angles unanswered gaps', 'thorough ... additionally chases the best leads'), adding latency expectations and citation-routing nuance, but those are behavioral facts rather than parameter-semantic enrichment. The description complements but does not meaningfully extend what the schema already conveys.

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 precise resource ('Pipeworx's 1500 STRUCTURED data sources'), a specific mechanism ('decomposes your question into focused facets, routes each ... IN PARALLEL'), and a concrete deliverable ('findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation'). It actively distinguishes itself from siblings by asserting 'this is NOT open-web search' and contrasting with ask_pipeworx, so an agent can separate it from the 30+ sibling tools without opening their schemas.

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 and when-not-to-use rules: 'For a single lookup use ask_pipeworx', 'For BREAKING or colloquial CURRENT-NEWS ... topics, prefer ask_pipeworx — it routes to live news APIs', and 'If you are not signed in, use ask_pipeworx instead'. It also states what it is best for ('broad/multi-part questions over structured data') and names exact alternatives from the sibling list, leaving no selection ambiguity.

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