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

Even though annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, the description adds substantial behavioral context: parallel call execution, exact financial data points pulled, handling of off-calendar fiscal years, sorting by primary metric, and citation URI return. This goes well beyond the 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 quite long but every sentence contributes unique information: usage examples, preference rule, type-specific data details, sorting behavior, and efficiency note. It is front-loaded with user phrasings. Slight verbosity in listing example phrasings prevents a perfect 5, but it is well-structured.

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?

With no output schema, the description fully explains what data is returned (paired data, citation URIs, sorted by primary metric). It covers complexity: multiple entity types, data sources, and edge cases like off-calendar fiscal years. Annotations handle safety, and the description handles everything else, making it complete.

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% with descriptions for both parameters, but the description enriches meaning significantly by defining what each type fetches (e.g., 'revenue + net income + cash + long-term debt' for company, 'FAERS adverse-event counts' for drug) and giving concrete examples like AAPL, MSFT, ozempic, mounjaro. This adds value beyond the schema.

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 the tool performs side-by-side comparison of 2-5 companies or drugs, with specific user phrasings and examples. It explicitly distinguishes from sequential single-pack lookups by mentioning 'one parallel call' and 'replaces 8–15 sequential lookups.'

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?

It provides explicit guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also clarifies the type-specific data sources (SEC EDGAR/XBRL for companies, FAERS/FDA for drugs), so the agent knows exactly when and how to use it.

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