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

Annotations already provide the readOnly/openWorld/idempotent safety profile, and the description adds substantial operational behavior beyond them: account/tier gating ('depth:"thorough" needs a paid plan'), latency ('Expect 15-60s... up to ~90s'), anti-hallucination behavior ('explicit gaps[]... never invented'), and citation resolvability ('present only when the source emits one that resources/read can actually serve'). No contradiction with the annotations.

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?

Although front-loaded with the most critical facts (auth requirement and fallback tool), the description is a single dense run-on block with heavy parenthetical nesting, a stranded fragment ('(one LLM call, not many)'), and three separate ask_pipeworx routing rules that could be consolidated. High information density but poor scaffolding — implementation details like citation_uri semantics and semantic excerpting are interleaved with routing guidance instead of being structurally organized.

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?

Since there is no output schema, the description correctly carries the return-format burden: 'findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[]', plus contradictions[], hop, and citation_uri fields. For a high-complexity tool it covers auth, tiers, alternatives, input shape, output structure, failure behavior, latency, and data freshness — a genuinely complete picture.

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 with the schema doing the heavy lifting. The description adds value above that baseline: it ties the 'thorough' depth to the paid tier, ties 'standard'/'thorough' to contradictions[] and gap-recovery behavior, and gives latency expectations per depth. It doesn't reach 5 because the schema's depth enum description already covers facet counts and hop behavior.

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+resource: 'Grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources... in ONE call', and explicitly differentiates from what it is not: 'this is NOT open-web search'. It names the sibling it is not — 'For a single lookup use ask_pipeworx instead' — so an agent can tell it apart from ask_pipeworx and entity_profile without opening 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?

Gives explicit when/when-not conditions with named alternatives: 'Best for broad/multi-part questions over structured data', 'If you are not signed in, use ask_pipeworx instead', 'For a single lookup use ask_pipeworx instead', and 'For BREAKING or COLLOQUIAL... topics, prefer ask_pipeworx'. Multiple exclusion conditions with the same alternative tool named — 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.