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

Even with readOnlyHint and idempotentHint annotations, the description adds substantial behavioral context: account/paid-plan requirements, parallel decomposition across 5,743 tools, explicit gaps[] rather than invented answers, semantic excerpting of large records, contradictions[] for some depths, citation fetchability guarantees, and expected latency of 15-90s. This goes far beyond the annotations and helps an agent predict side effects and constraints.

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 dense and purposeful; every sentence carries operational information an agent needs: prerequisites, alternatives, scope, mechanism, output shape, limits, depth trade-offs, and latency. It is front-loaded with the account requirement and the fallback alternative, then builds into the mechanics and output details. No fluff or repetition that would dilute its value.

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?

Given there is no output schema, the description compensates thoroughly by enumerating the findings packet fields, gaps[], contradictions[], citation behavior, and timing expectations. It also covers prerequisites, tier differences, and when not to use the tool. An agent has enough context to invoke deep_research correctly and judge whether the result is appropriate, even without an output schema.

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 meaningful usage-oriented semantics beyond the schema: depth:'thorough' requires a paid plan, standard/thorough return contradictions[], standard performs a gap-recovery hop, thorough chases leads, and broad/multi-part questions are explicitly supported because decomposition is the point. This is more than the schema alone provides.

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 opens by scoping the tool precisely: 'Grounded multi-source research across Pipeworx's 1500 STRUCTURED data sources' in one call, distinct from open-web search. It also names the deliverable—a findings packet with verbatim evidence, confidence, source, fetched_at, and citations—so an agent clearly understands what deep_research does and how it differs from siblings.

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 routing guidance: 'If you are not signed in, use ask_pipeworx instead' and 'For a single lookup use ask_pipeworx.' It also states when deep_research is best ('broad/multi-part questions over structured data') and contrasts it with open-web search, leaving no ambiguity about when to select this tool over alternatives.

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