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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful behavioral context beyond these: it clarifies the tool returns metadata only (not data values), details the returned fields (title, description, unit, timestamp, variables with codes/labels), and positions it as a prerequisite for querying. No contradictions 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 average but every sentence earns its place: purpose, return details, workflow, and common table IDs. It is front-loaded with the core purpose. The common table list partially duplicates the schema's examples, but still adds value by describing what each table contains.

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 one-parameter metadata lookup tool with a rich schema description and an output schema present, the description is complete. It covers what the tool returns, why it is needed, how to obtain the parameter, and the surrounding workflow. No critical information is missing.

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?

The single parameter table_id is fully described in the schema (100% coverage), including how to obtain it and common examples. The description augments this with additional common table IDs and human-readable meanings (e.g., 'FOLK1A' quarterly population), which helps an agent select a meaningful value. Baseline is 3 due to schema coverage; the extra examples and workflow context justify 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 states a specific action ('Get the full metadata') on a specific resource ('a specific Statistics Denmark table') and specifies the key outputs: dimension codes, valid value codes, and labels needed to construct a data query. It explicitly distinguishes itself from siblings by placing itself in the workflow between data.tables and data.query.

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?

Usage guidance is explicit: 'This is the required second step before querying data' with an ordered call sequence naming statistics-denmark.data.tables, table_info, and query. This clearly tells an agent when to invoke this tool versus alternatives, leaving nothing to inference.

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