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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the unknown-topic error behavior, payload differences between 'full' and 'schema', default main_topic, and semantic hazards such as non_additive columns, value_implications, and has_total/requires_single_value. No annotation contradiction exists.

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 information-dense and front-loaded with the core purpose, but it is delivered as one long unbroken paragraph with many semicolon-separated clauses. Every piece of information earns its place, yet it would be much easier for an agent to scan with bullets or short sectioned sentences.

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 output schema exists and this is a metadata/read tool, the description is remarkably complete. It covers payload shape, verbosity behavior, error handling, default parameters, and important semantic warnings around aggregation. An agent has enough context to call this tool correctly and interpret its result.

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 only 33%, so the description must compensate. It adds meaning for verbosity ('full' vs 'schema' payload tradeoff), main_topic defaults and high-level routing to education/census/immigration, and topic failure behavior. It stops short of enumerating valid topic identifiers, but the self-describing error makes them discoverable.

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 states a specific verb+resource: it returns the full schema for one topic. It enumerates the exact output components (columns, filters, foreign_keys, key_metric, recommended_query) and positions itself as the authoritative metadata endpoint to read before query_dataset, distinguishing it from data-returning siblings.

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 explicit sequencing guidance: 'read this before query_dataset' and prefers 'full' before reporting conclusions. It also says to use verbosity='schema' when only filter keys and enums are needed. However, it does not explicitly compare against describe_dimension, list_datasets, or search_datasets, so it lacks a full routing matrix.

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