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

Beyond the readOnly/idempotent annotations, the description discloses specific data sources (SEC EDGAR/XBRL for companies, FAERS/FDA for drugs), return behavior (sorted by primary metric), and output details (paired data + citation URIs). It also handles edge cases like off-calendar fiscal years, providing rich behavioral context not evident from annotations.

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 dense but every sentence earns its place: trigger phrases, explicit preference guidance, type-specific details, sorting behavior, and citation output. It is front-loaded with the most critical information (what it does and when to prefer it), and despite length, it is structured and free of fluff.

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 moderate complexity (two types, no output schema), the description covers all essential aspects: purpose, usage context, data sources, result ordering, and return format. It effectively compensates for the lack of an output schema by stating that paired data and citation URIs are returned, making it fully self-contained for an agent.

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 baseline is 3. The description adds meaningful semantics by explaining what each 'type' value does (pulls 10-K vs FAERS data), which clarifies the expected entity types and the nature of the comparison. It reinforces the schema's parameter descriptions without repeating them verbatim, earning a 4.

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 it performs side-by-side comparison of 2–5 companies or drugs in one call, with specific verbs like 'compare' and 'rank'. It distinguishes from siblings by explicitly saying 'ALWAYS PREFER over sequential single-pack lookups' and handles two entity types (company/drug) with distinct data sources.

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?

Provides explicit when-to-use guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also gives trigger phrases ('X vs Y', 'which is bigger') and explains the tool's advantage ('Replaces 8–15 sequential lookups'). This makes the intended usage clear without needing to consider alternatives.

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