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

Annotations already mark the tool readOnly, idempotent, openWorld, and non-destructive. The description adds significant behavioral context beyond this: the parallel fan-out across many sources, the role of sources_used/sources_failed in distinguishing real no-data from bugs, the resolved:false + notes behavior for private companies, and the expected empty fda_products section for companies without licensed biologics. These details are essential for interpreting results and are not available in annotations or schema.

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 front-loaded with trigger examples and the primary use case before the dense output breakdown. Every clause about a source or edge case earns its place given the tool's complexity. It loses a point for being somewhat over-stuffed, including a garbled 'sorted?' fragment and an inline enumeration of all source sections that could have been tightened.

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, multi-source tool with no output schema, the description is near-complete: it explains what each source contributes, how to interpret empty sections, how failures are signaled, what input shapes are accepted, and the parallel execution model. Minor omissions like latency or rate limits are acceptable given the readOnly and idempotent annotations.

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%, and the schema already describes type and value well, so the baseline is 3. The description adds real value by spelling out the accepted shapes (ticker, zero-padded CIK, company name), the SEC EDGAR company-name resolution, the interchangeability of type values, and the private-company outcome. This is above baseline but not a huge uplift since the schema covers most parameter meaning.

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 concrete trigger phrases ("Tell me about X", "research Acme") and defines a precise deliverable: a full cross-source profile of a US public company in one parallel call. It explicitly lists the output sections (cik, recent_filings, fundamentals, patents, etc.), making the tool's scope and resource unambiguous and clearly distinct from the sibling tools.

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 an explicit selection rule: "ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view." It also specifies accepted input forms and the private-company fallback, clarifying applicability. However, it doesn't name sibling alternatives for narrower tasks (e.g., resolve_entity), which prevents a perfect score.

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