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

Goes well beyond the readOnly/idempotent annotations by naming data provenance (SEC EDGAR/XBRL for companies, FAERS + FDA approvals + trial counts for drugs), disclosing the off-calendar fiscal-year handling, the sort order (primary metric descending so "largest" reads off the top), and the citation URIs returned. That is exactly the behavioral context annotations cannot express.

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?

Front-loaded with the natural-language triggers, then capability, then return shape — good ordering with no filler sentences. The trigger-phrase enumeration is long and slightly redundant across "vs"/"versus"/"versus X", costing a bit of density without adding information.

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?

No output schema exists, and the description compensates by describing the return: paired data sorted by the primary metric plus per-entity pipeworx citation URIs. Combined with the annotations and full schema coverage, an agent needs nothing else to invoke 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?

Schema coverage is already 100%, yet the description still adds meaning: it explains what type="company" retrieves (10-K revenue, operating income, net income, cash, long-term debt) versus type="drug" (adverse-event, approval, trial counts), and clarifies value formats (tickers/CIKs vs drug names). It does not add anything about the 2–5 boundary beyond what the schema's minItems/maxItems already state.

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?

States a specific verb and resource ("side-by-side comparison of 2–5 companies or drugs in ONE parallel call") and enumerates the query shapes it answers ("X vs Y", "which is bigger", "rank these companies"). It is clearly separable from siblings like entity_profile, company_facts and archive_compare, which are single-entity or archive-scoped.

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?

Explicit routing rule: "ALWAYS PREFER over sequential single-pack lookups when comparing entities," plus the cost argument "Replaces 8–15 sequential lookups." The agent is told both when to pick this tool and which pattern it supersedes.

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