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

Beyond the readOnly/openWorld/idempotent annotations, the description details what the tool does and does not do: it never invents answers, returns explicit gaps[], provides fetchable citation_uris only when resolvable, and includes contradictions[] for standard/thorough. It also discloses auth/account requirements and the paid thorough tier, making side effects and constraints clear.

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 and dense, but nearly every sentence adds a distinct operational fact: use-case boundaries, depth behavior, citation semantics, gap handling, excerpting, and latency. It is not padded with filler, though some repetition of the ask_pipeworx comparison and pipeworx:// 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?

Given the tool's complexity, the description covers the full decision surface: when to use it, when not to, how each depth tier behaves, what the response packet contains, how citations are resolved, how missing data is handled, and expected timing. It also addresses limitations like current-news coverage and paid thorough tier, so an agent has enough context to call it correctly.

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?

The schema already covers question and depth with 100% coverage, so the description is not the only source of parameter meaning. However, it adds valuable semantics by explaining that questions may be broad/multi-part, that quick=3 facets, standard adds gap recovery and contradictions, and thorough adds iterative lead-chasing—making depth behavior far more actionable than the enum alone.

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 clearly states that deep_research decomposes broad/multi-part questions, routes facets to many tools in parallel, and returns a grounded findings packet with citations, gaps, and contradictions. It explicitly distinguishes itself from ask_pipeworx for single lookups and news topics, so an agent can pick the right tool without opening the schema.

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?

It gives explicit when-to-use guidance: best for broad/multi-part structured-data questions, while single lookups and breaking/current-news topics should go to ask_pipeworx. It also explains the depth tiers, gap-recovery behavior, and expected latency, leaving little ambiguity about how to invoke it.

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