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

Even with strong annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description adds substantial behavioral context: account/paywall requirements, the internal process of decomposition and parallel routing, the findings packet structure with verbatim evidence/confidence/source/fetched_at/citations, the gaps[] guarantee of never inventing answers, contradictions[] behavior, semantic excerpting for large records, and explicit latency expectations (15-60s, up to ~90s). No contradictions 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 densely packed with decision-relevant information, and it is front-loaded with the most critical operational constraint (account required and the alternative if not signed in). Every section earns its place given the tool's inherent complexity (depth modes, citation semantics, gaps/contradictions, latency). It loses one point because some parentheticals and repeated depth-mode details could be tightened without losing meaning.

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 tool with no output schema, the description does an excellent job explaining what the agent will receive: a findings packet with evidence, confidence, source, fetched_at, citations, gaps[], contradictions[], and a `hop` field. It also covers prerequisites (sign-in, paid tier), timing, and important caveats like large-record excerpting and fetchable citation URIs. Nothing critical for invoking this tool 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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by adding pricing implications for 'thorough' ('depth:"thorough" needs a paid plan'), explaining depth-level behavior differences ('standard' adds a gap-recovery hop; 'thorough' additionally chases leads), and elaborating on what makes a good question ('Broad/multi-part is fine'). This extra semantic context justifies a 4.

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 states a specific verb and resource: grounded multi-source research across Pipeworx's 1517 structured data sources in one call. It distinctly separates this from open-web search and explicitly positions it against the sibling ask_pipeworx with 'For a single lookup use ask_pipeworx instead.' The facet decomposition and parallel routing behavior further clarify exactly what the tool does.

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 guidance ('Best for broad/multi-part questions over structured data'), when-not-to-use guidance ('For a single lookup use ask_pipeworx instead'), and a concrete alternative for unauthenticated users ('If you are not signed in, use ask_pipeworx instead — it works on every tier'). It also warns about the paid-plan requirement for the 'thorough' depth, which is exactly the kind of decision-relevant information an agent needs.

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