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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: that 'unknown' counts as not in place until verified, that questions should be presented incrementally rather than dumped, and that scoring is a separate follow-up call. That is exactly the extra context the annotations cannot convey.

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?

Two sentences, front-loaded with the trigger and then the payload specification. The field enumeration ('id, area, why it matters, its weight and the legal references') is dense but earns its place since no output schema exists. Slightly long, but no padding.

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 7-parameter tool with no output schema, the description fully compensates: it specifies the shape of each returned question, the conversational protocol for collecting answers, the meaning of the ambiguous 'unknown' value, and the handoff to score_assessment. An agent could execute the whole flow from this text alone.

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 every parameter including the enum and defaults is already documented in structured form. The description contributes a light framing — that the jurisdiction/AI booleans determine 'an organisation's profile' which filters the question set — but does not clarify defaults such as freeOnly (free vs. full assessment) or the lang parameter beyond what the schema says. Baseline 3 applies.

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 concrete resource — the EasyLPD self-assessment questions that apply to an organisation's profile — and enumerates the fields each question carries (id, area, why it matters, weight, legal references). It implicitly separates itself from fadp_questions by naming the EasyLPD assessment, but never explicitly tells the agent how the two question sets differ.

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 gives an explicit trigger ('Use when someone wants to check where their organisation stands with data protection'), an operational procedure ('Ask them in the conversation, a few at a time'), the accepted answer vocabulary, and a named next step ('then call score_assessment'). No inference is required to know 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.