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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint/destructiveHint, and the description adds substantial context beyond those: account and plan requirements, parallel routing across tools, output structure with evidence/citations/gaps/contradictions, fetchable citation URIs, large-record excerpting, and timing expectations. This gives the agent a faithful model of the tool's behavior.

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 and dense, but nearly every sentence adds a distinct piece of selection or invocation-relevant information. It is front-loaded with the access constraint and core scope, then proceeds to usage guidance, output behavior, and edge cases. The density is justified for a complex tool, though it could be tightened.

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?

There is no output schema, yet the description fully explains return semantics: a findings packet with verbatim evidence, confidence, source, fetched_at, stable pipeworx:// citations, gaps[], contradictions[], hop fields, and fetchable citation_uri. It also covers failure-ish cases like topics absent from the catalog and timing expectations, leaving no critical ambiguity for an agent deciding whether to call it.

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, but the description enriches parameter understanding by explaining the practical meaning of depth levels (hop structure, gap recovery, contradiction scanning), the paid prerequisite for 'thorough', and the additional hop/citation fields that appear on results. It doesn't fully rely on the schema and adds genuinely useful selection nuance.

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 the tool performs grounded multi-source research across Pipeworx's structured data sources in one call, and explicitly differentiates it from open-web search and the sibling ask_pipeworx. It names the resource (structured data catalog), the action (research), and the distinguishing decomposition/parallel-tool behavior.

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 guidance: use ask_pipeworx for single lookups, use ask_pipeworx when not signed in, prefer ask_pipeworx for live news topics, and use deep_research for broad/multi-part structured-data questions. It also clarifies the account/paid-plan prerequisite.

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