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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses cost ('FREE'), the non-protocol-error behavior ('never raises a protocol error; returns {"error": ...}'), recovery guidance, and the meaning of verified_on. These are precisely the traits an agent cannot infer from structured fields.

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?

Front-loaded purpose and cost, then usage, then behavior notes — good ordering with no filler. The inline output sample is slightly redundant given an output schema exists, though it does make the regime object shape concrete.

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?

Covers purpose, cost, usage trigger, downstream consumers, error semantics, retry safety, and scope caveat. Nothing an agent needs in order to call a zero-parameter read tool correctly 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?

Zero parameters, so the baseline is 4. The description still shows the canonical empty input {} and what the resulting object contains, which clarifies that no filtering or arguments are needed.

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?

States a specific verb and resource ('List the reporting regimes this server can compute, with citations') and immediately distinguishes itself from siblings by naming compute_deadlines and classify_event as the consumers of its output. An agent knows exactly what this returns and why it exists.

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?

'Use when choosing the regime id and event_type for compute_deadlines or classify_event' gives an explicit trigger condition plus the downstream tools, which is the real selection logic for a discovery tool. The 'Not for legal advice' line sets the boundary of what the results may be used for.

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