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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true, idempotentHint=false), and the description adds genuinely non-obvious behavior: results come from persisted CSI history and may change as new transitions are recorded, no live scans are performed, and no state is modified — which also explains the non-idempotent hint. It further guards against misreading `REMOVED` as proof of a vendor switch or cancellation.

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 verb and resource, then the event definitions, then clearly delineated USE WHEN / DO NOT USE WHEN blocks, then freshness caveats. Every sentence carries distinct information; the enumerated siblings are dense but each is necessary for routing.

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 read-only lookup with a full output schema, rich annotations, and 100% schema coverage, the description supplies everything else an agent needs: what counts as an event, what it does not prove, when to prefer a sibling tool, and the data-freshness caveat. No material gaps remain.

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%: start/end boundaries, the 1-100 limit with default 100 and no pagination, and vendor normalization (judge.me -> judgeme) are all documented in the schema itself. The description only restates the UTC time-window framing, so baseline 3 applies — it adds no parameter detail beyond structured fields.

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 (Retrieve) and resource (confirmed customer adoption changes for a vendor in a UTC window) and then defines the two event types with precise domain semantics (`ADDED` = `ABSENT -> PRESENT`, `REMOVED` = `PRESENT -> ABSENT` in STRAELO CSI observations). It also explicitly rules out the two most confusable siblings, so the agent can distinguish this from vendor_customer_confirmed_lookup and vendor_customer_transition_signal_lookup without opening schemas.

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?

Contains an explicit USE WHEN clause (historical evidence of adoption/removal during a period) and a DO NOT USE WHEN clause naming three concrete alternative tools with the condition that selects each. Nothing about tool choice is left to inference.

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