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

Exceptionally transparent: decomposition into parallel sub-queries, deterministic routing, returns gaps[] and never fabricates answers, includes hop semantics, contradiction scan for deeper levels, citation URIs with source/fetched_at, and excerpting of large records. This far exceeds the readOnly/idempotent/destructive annotations and adds genuinely non-obvious behavior.

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?

Dense but every clause earns its place: auth requirement, tier caveat, scope boundary, output contract, behavior guarantees, and routing guidance. Slightly long, but front-loaded with the most critical constraint (account required) and remains skimmable.

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?

With no output schema, the description does the work: it enumerates exactly what each finding contains (verbatim evidence, confidence score, source, fetched_at, citation URI), explains the gaps[] contract, and covers auth, scale limits, and parallelism. Nothing operationally important 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?

Input schema already describes 'question' and the 'depth' enum, but the description supercharges them: thorough = 'chase the best leads', standard = 're-angles unanswered facets', plus timing expectations and a concrete example query. It tells the agent how to choose depth in context, which is beyond anything in the schema.

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, action-oriented framing: 'grounded multi-source research' across 5,937 tools and 1,547 named source categories (SEC filings, FRED, markets, etc.). It clearly differentiates from ask_pipeworx ('single lookup') and open web search ('returns mostly empty gaps[]'), so an agent knows exactly what it is and is not.

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 deep_research ('broad or multi-part questions over the structured catalog') and when NOT to ('single lookup → ask_pipeworx'; 'recent current-events → ask_pipeworx'). Even explains failure mode (empty gaps[] for uncatalogued topics). This is textbook usage guidance with named alternatives.

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