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

Annotations already mark the tool read-only and non-destructive; the description adds valuable non-obvious behavior: paid products debit a prepaid credit key, failures are never charged, sample=true returns a free real answer, and each product's schema lives in the catalog. It also enumerates the broad coverage domains and clarifies that every product is reachable by id. No contradiction with 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 longer than minimal, but each block earns its place: primary action, workflow, example, coverage list, catalog schema pointer, billing behavior, and sample option. The coverage list is somewhat long, but it is useful for a broad dispatch tool; the most actionable instructions are front-loaded.

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 generic gateway over 137 products, this is complete: it explains how to discover ids, how to pass params, where per-product input/output schemas live, billing behavior, and how to sample before paying. The output schema is intentionally delegated to the catalog, and annotations already cover the safety profile.

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?

With schema description coverage at 0%, the description fully compensates. It explains product_id is found via answerpool_search_catalog, params is a JSON object (with a concrete weather_alerts example), and sample is a boolean that returns a free real answer. The example ties all three parameters together in one usable shape.

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 starts with the specific action 'RUN ANY of the 137 AnswerPool products by id' and clearly distinguishes this execution tool from answerpool_search_catalog, which is used to find ids. It is not a tautology of the title; it communicates that this is the universal gateway to all products.

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 explicitly describes the intended workflow: use answerpool_search_catalog to find an id, then call this tool with product_id and params, calling it the 'main path.' It does not, however, discuss when to prefer specialized siblings like answerpool_sec_company or when to use answerpool_list_products, so exclusions are not fully explicit.

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