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

Annotations already mark readOnly/openWorld/idempotent, and the description adds non-obvious traits: returns a findings packet with 'verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation', 'explicit gaps[] for facets the data couldn't answer (never invented)', native contradictions[] listing, semantic excerpting, hop fields, and expected latency 15-60s up to 90s. It also discloses the paid-plan gate for depth:'thorough'.

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, front-loading the account requirement and sibling fallback before the core capability, then depth semantics and edge behavior. Almost every clause adds operational guidance, though the formatting is a single dense block that could be tightened with structure.

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?

For a complex tool with no output schema, it covers invocation prerequisites (account, paid tier), expected output shape (findings packet, gaps, contradictions), return-value edge cases (citation_uri present only when resolvable), failure mode for non-catalog topics, and latency. Nothing an agent needs to decide or call 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 covers 100% of params, so baseline is 3; the description goes beyond by explaining what each depth means in behavioral terms (quick=3 single hop, standard=3 with gap-recovery + contradictions, thorough=6 paid iterative hop + contradictions) and clarifies that the question may be 'Broad/multi-part' because decomposition is built in. It also flags the paid constraint on thorough, which the schema enum alone doesn't convey.

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?

Description states a concrete capability: 'Grounded multi-source research across Pipeworx's 1495 STRUCTURED data sources ... in ONE call' and explicitly disambiguates 'this is NOT open-web search.' It names the unique mechanism (facet decomposition, parallel routing to 5,714 tools) and contrasts with sibling ask_pipeworx, so an agent can distinguish it.

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?

Gives explicit selection criteria: 'Best for broad/multi-part questions over structured data' and tells the agent to prefer ask_pipeworx for 'a single lookup' and for 'BREAKING or colloquial CURRENT-NEWS' topics. It also states the auth precondition and fallback: 'If you are not signed in, use ask_pipeworx instead.'

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