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

Annotations already mark readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, and the description adds substantial behavioral context without contradicting them: parallel decomposition across 5,798 tools, a findings packet structure, explicit gaps[] for unanswered facets, never invented, contradictions[] for standard/thorough, semantically excerpted large records rather than head-truncation, estimated latency per depth, and a citation_uri only when the source emits a fetchable record URI. This goes far beyond the annotations and materially helps an agent predict 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?

The description is long but earns most of its length: the account requirement, the alternative tool, the resource scope, the decomposition mechanism, the return-packet composition, latency expectations, and depth-tier differences are all decision-relevant for an agent. Some phrasing is convoluted (e.g., the parenthetical 'standard' vs 'thorough' depth explanation inside the depth property, and the run-on sentence about `hop`), so it is not maximally crisp. It is front-loaded with the account requirement and the key alternative, which is the right priority.

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 high complexity, the lack of an output schema, and the 2-parameter input, the description covers everything an agent needs to select and invoke it correctly: auth prerequisite, fallback tool, supported question types, depth semantics, latency, gaps/contradictions behavior, citation fetchability, and long-record handling. Return values are described sufficiently 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 schema already defines both parameters. The description still adds meaning: it clarifies that 'question' may be broad/multi-part because decomposition is intended, and it gives concrete examples of the depth tiers' behavioral differences (quick=single hop, standard=gap-recovery hop + contradictions[], thorough=paid iterative hop). That is a meaningful addition over the enum labels alone, though it does not explain the exact output format or the structure of the `hop` field.

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 ('research'), a resource ('Pipeworx's 1517 STRUCTURED data sources'), and an explicit scope ('NOT open-web search'). It distinguishes from siblings by naming ask_pipeworx as the alternative for signed-out users and positions itself as the multi-source parallel research tool, so an agent can select it correctly 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?

The description gives explicit when-to-use guidance: broad or multi-part questions over structured data ('compare X and Y...', 'research the filings + market picture...'). It also states exclusions and alternatives: if not signed in use ask_pipeworx; for a single lookup use ask_pipeworx; this is not open-web search. Depth tiers carry clear behavioral trade-offs (single hop vs gap-recovery vs paid iterative hop), so an agent knows when to choose which variant.

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