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

Beyond the readOnlyHint annotation, the description discloses important behavioral details: rates are per 1,000 registrations and null for seats with no registrations; network percentiles include all seats with registrations, counting no-findings as 0; snapshot_date is null for unscanned seats. These edge cases and calculation semantics are not available from annotations or schema.

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 moderately detailed but front-loaded with a clear one-sentence summary, followed by necessary semantic clarifications. The narrative about the Peppol Authority's scan adds context but is slightly embellished; still, every substantive sentence provides definitional or edge-case value.

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?

With no output schema, the description does the work of explaining what the tool returns: registrations, OPEN findings by rule, daily trend, and network comparison. It also defines null behavior and the daily rollup semantics. It stops short of an explicit response shape, but for a scorecard tool this is a strong, usable description.

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 description coverage is 100%, so the baseline is 3. The schema already documents seatId and days with examples and bounds. The description adds conceptual context around daily rollups and rate calculation, but does not add new parameter-level meaning beyond what the schema states.

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?

Description opens with a specific verb and resource: 'Get a seat's compliance scorecard.' It then enumerates the content (registrations, OPEN findings by rule, daily trend, network position), making it clear this is a single-seat compliance view, distinct from sibling tools like get_compliance_stats or list_compliance_findings.

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 clear context: it is a per-seat compliance posture, described as what a Peppol Authority's periodic scan reports. It does not explicitly name alternatives or state when not to use it, but the scope ('One seat's compliance posture') differentiates it from network-level siblings.

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