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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, and the description adds substantial behavioral context beyond these: account/paywall requirements ('depth:"thorough" needs a paid plan'), parallel routing mechanics ('routes each to the right one of 5,798 tools IN PARALLEL'), the full output contract (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), gap handling ('explicit gaps[] ... never invented'), citation fetchability guarantees (citation_uri 'present only when the source emits one that resources/read can actually serve'), contradictions[] behavior, semantic excerpting ('not head-truncated'), and latency ('15-60s... up to ~90s'). This is rich behavioral disclosure far beyond what annotations carry.

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 text is dense and every sentence contributes: account requirements, sibling routing, decomposition mechanics, output format, gap handling, depth behavior, citation guarantees, excerpting policy, and latency. Critical info (account required, alternative tool) is front-loaded. However, it is a single stream-of-consciousness paragraph with no line breaks or sectioning; a ~250-word wall of text is harder to parse than the same content in structured form, so it doesn't earn a 5.

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?

This is a complex tool (2 params, a 3-value enum, no output schema, and 30+ siblings), yet the description covers everything an agent needs to call it correctly: the full return shape (findings packet fields, gaps[], contradictions[], hop, citation_uri), depth semantics, auth and tier restrictions, sibling routing rules, latency, and failure modes (mostly empty gaps[] on non-catalog topics). Without an output schema, the description fully shoulders the burden of explaining return values, and it does.

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 genuine value beyond the schema: it ties depth levels to pricing ('thorough needs a paid plan'), to latency expectations, and to behavioral outcomes ('quick=3 facets... standard=3 adds a gap-recovery hop... thorough=6 adds a full iterative hop'). The schema already documents facet counts and hops, so the marginal value is moderate but real — hence 4 rather than 5.

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+resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources' in ONE call. It explicitly distinguishes itself from siblings by declaring 'this is NOT open-web search' and by naming what it is NOT ('For a single lookup use ask_pipeworx', 'For breaking news... prefer ask_pipeworx'). The scope ('broad/multi-part questions over structured data') is unmistakable and separates it from every sibling listed.

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 provides explicit when-to-use and when-not-to-use conditions with named alternatives: 'If you are not signed in, use ask_pipeworx instead', 'For a single lookup use ask_pipeworx', and 'For breaking news / market-moving events / ... prefer ask_pipeworx'. It also gives concrete example queries ('compare X and Y's regulatory + financial exposure'). An agent has zero ambiguity about routing.

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