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

Even though annotations already indicate readOnly/openWorld/idempotent, the description goes far beyond: it discloses account/auth requirements, paid tier for 'thorough', latency expectations, the gap recovery and contradictions[] behavior, the hop field and citation_uri semantics, and the fact that large records are semantically excerpted to relevant passages (not head-truncated). It also explicitly says findings are never invented, and that citations are only present when fetchable. 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 dense but front-loaded with critical information (account/pricing gate, alternative tool). Every sentence carries operational meaning. A bit long and somewhat run-on in places (e.g., 'ACCOUNT REQUIRED (free — sign in...' mixed with depth-level policy), but the density justifies the length; trimming would risk losing important behavioral detail.

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 2 params and no output schema, the description supplies everything an agent needs: when to use it, when not to, what it returns (findings packet, gaps[], contradictions[], hop fields, citation URIs), latency, authentication, and the difference from open-web search. No output schema means the description must carry return semantics, and it does thoroughly.

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 schema already documents both parameters well. However, the description adds meaningful context on top: how depth affects hop behavior, paid tier implications for 'thorough', and how the question parameter's broad/multi-part nature maps to decomposition. That exceeds the baseline expected when schema coverage is high.

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 with a precise verb ('Grounded multi-source research'), specifies the exact resource (Pipeworx's 1504 structured data sources), and draws a sharp contrast with open-web search. It names concrete example queries. It also clearly distinguishes itself from sibling ask_pipeworx, saying directly 'this is NOT open-web search' and 'For a single lookup use ask_pipeworx instead.'

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 and when-not-to-use guidance. It says ask_pipeworx is the alternative when not signed in, and for 'BREAKING or CURRENT-NEWS topics' prefer ask_pipeworx because deep_research returns gaps[] for topics not in the structured catalog. It even explains depth levels as second-hop iterations. This is exemplary routing behavior.

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