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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds two genuinely new behavioral facts: a personal-data opt-in is required, and every request is access-logged (an audit consequence an agent should know before calling). It also discloses the specific PII returned per record type, which is above the annotation bar, though it says nothing about empty-result or not-opted-in failure behavior.

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 purpose is front-loaded in the first clause, but the body is one long run-on sentence with dense nested parentheses and semicolons that takes effort to parse. Every clause carries information, yet the structure works against quick scanning.

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 15-parameter PII tool with no output schema, the description covers the essentials an agent needs: the opt-in gate, audit logging, and what each record type returns. Remaining gaps are pagination behavior across many filters and the meaning of pii_cleared, but those are handled in the schema.

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?

With 93% schema description coverage the schema already documents nearly every parameter, so the baseline is 3. The description contributes the record-dependent meaning (orders joins on ebay_orders.order_id and yields buyer/ship-to PII; messages returns list-with-snippet vs full thread ordered oldest-first), but leaves limit/cursor, window_days, country_codes, fulfillment_status and pii_cleared entirely to the schema.

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 resource and scope: personal data of the seller's *own* buyers and customers, keyed by target and record, then enumerates the eBay record types (orders, messages) with the fields each returns. This is clearly distinguishable from get_marketplace_data, though the description never names that sibling explicitly to draw the contrast.

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 a prerequisite (needs the personal-data opt-in) and an implicit branch rule: omit conversation_id for the messages list, pass one for a full thread. It does not say when to prefer this over get_marketplace_data, get_entities, or get_events, so the agent must infer the boundary from the resource names alone.

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