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

Annotations already declare readOnly/openWorld/idempotent/non-destructive. The description adds substantial behavioral context: account/payment requirement, expected latency (15-60s, ~90s for thorough), gap[] handling with 'never invented', contradictions[] for standard/thorough, citation_uri resolvability guarantee, and semantic excerpting. It even discloses a failure mode (empty gaps for off-catalog topics). No contradiction with 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?

The description is long but information-dense and front-loads the most critical constraint (account/auth + fallback). The figures '1,500 sources' and '5,743 tools' add promotional color but are not directly actionable. Each clause does inform selection or behavior, so it is well-structured; slightly over-polished for a minimal definition, but far from bloated.

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, so the description must explain return values. It names the findings packet fields (verbatim evidence, confidence, source, fetched_at, pipeworx:// citation, gaps[], contradictions[], hop, citation_uri) and covers latency, depth semantics, and off-catalog behavior. The only minor gap is that the exact output JSON structure isn't specified, but all key calling decisions are addressed.

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%, including detailed descriptions for depth and question, so baseline is 3. The description adds genuine beyond-schema value: 'thorough' requires a paid plan, latency ranges per depth, and the meaning of hop/citation_uri fields. It enriches the parameters without duplicating what the schema already says.

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 uses a specific verb ('research') and names the resource (Pipeworx's 1500 structured data sources), and explicitly differentiates from siblings: 'this is NOT open-web search' and contrasts with ask_pipeworx. It also states what it returns (findings packet with evidence, confidence, source, citation). This is far beyond a vague or tautological statement.

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?

Explicitly states when to use it ('Best for broad/multi-part questions over structured data'), when not to ('For a single lookup use ask_pipeworx'), and for breaking news topics 'prefer ask_pipeworx'. It also names a hard prerequisite: if not signed in, use ask_pipeworx instead. Multiple named alternatives and conditional exclusion clauses earn full marks.

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