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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavior: default and maximum page size, an ~8,000-token page budget with approx_tokens per page, next_cursor continuation, a required records:read scope, and zero credit cost on refetch. That is exactly the extra context annotations cannot carry.

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 with the core behavior and pagination, which is good, but it is one dense paragraph bundling five unrelated topics. The closing sentence on UK GDPR Article 6(1)(f) lawful basis and PECR corporate-subscriber filtering concerns sending to audiences, not fetching records, and does not earn its place in this definition.

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 paged, read-only fetch with a full schema and an output schema, the definition covers what an agent needs: pagination mechanics, page-size limits, format choice, auth scope, and credit cost. The only loose end is how 'fields' interacts with the order's default field set, which the schema only partly resolves.

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 the baseline is 3, but the description adds rationale the schema lacks: the 100-record cap exists to keep a page under ~8,000 tokens, and the cursor is the next_cursor from the previous response. It does not explain 'fields' or the order_id readiness requirement beyond the schema, so it stops short of a 5.

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 ('Returns a page of an order's delivered records') plus the scope of what comes back (licence block on every page, JSON or CSV). An agent knows immediately this is a paged read of one order's delivered records, distinct from order creation or compliance-receipt tools.

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?

Gives workflow context ('Call check_suppression before any send, and get_compliance_receipt for proof of screening') and a cost rule ('Fetching again under licence costs 0 credits'), which implies refetching is cheap. However, it never contrasts with the closest sibling, preview_records, or states when not to use this fetch — the when-to-use guidance is implied rather than explicit.

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