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

Even though annotations provide readOnlyHint=true and destructiveHint=false, the description adds substantial behavioral detail beyond those: account/plan requirements, parallel decomposition across 5,798 tools, the findings packet structure (verbatim evidence + confidence + source + fetched_at + pipeworx:// citation), explicit gaps[] for unanswered facets, contradictions[] for standard/thorough, semantic excerpting rather than head-truncation, and expected latency (15-60s, up to ~90s). This is far more transparent than the annotations alone.

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 every section earns its place: account gate, core mechanism, output shape, depth semantics, latency. It is front-loaded with the most decision-critical facts (account required, alternative tool) and uses examples to illustrate rather than pad. Some redundancy exists where the depth parameters are explained in both the description and the schema, and the dense parenthetical about 'hop' and 'broken' citations could be cleaner, but overall it is well-organized for its size.

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 complex research tool with no output schema and only 2 parameters, the description is unusually complete. An agent knows the input format, the output shape (findings packet, gaps[], contradictions[], citations), the latency, the auth/plan constraints, the semantic excerpting behavior, and the key caveat that citations are only included when the source emits a resolvable URI. No critical operational fact 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 coverage is 100%, so the schema already documents both parameters thoroughly. However, the description adds meaning beyond the schema by explaining what each depth level actually does: quick=3 single hop, standard=3 with gap-recovery and contradictions, thorough=6 paid with iterative lead-chasing. This helps an agent pick the right enum value. The question parameter is contextualized by the 'broad/multi-part is fine' framing and examples, though that is less critical for a free-text 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 and resource: 'Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources... in ONE call.' It explicitly says what it is not ('this is NOT open-web search') and gives concrete example questions like 'compare X and Y's regulatory + financial exposure,' which clearly distinguishes it from siblings like ask_pipeworx and search_within.

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 explicitly says when to use the tool: 'Best for broad/multi-part questions over structured data' and when not to: 'For a single lookup use ask_pipeworx instead.' It also names the specific alternative (ask_pipeworx) with a condition (if not signed in), plus it warns that 'thorough' depth requires a paid plan. This gives an agent both positive and negative selection criteria.

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