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

Beyond readOnlyHint, it discloses ordering, expiry filtering, admin-only fields, the eventId/identificationId mapping for reported sales, and posRef scoping. It still omits pagination or default limit behavior, so it is not exhaustive.

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?

It is front-loaded with 'Who is at the till' and packs useful return-field context into a short block. However, the main sentence is very dense with nested parentheticals, so structure could be cleaner.

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?

No output schema exists, so the description carries the return-value burden; it enumerates fields and explains the eventId/identificationId relationship. It is nearly complete for invocation, with only default limit or pagination behavior notably absent.

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 67%; orgId and posRef are already described in the schema, and the description repeats posRef's narrowing behavior but adds little for orgId or limit. With one of three parameters undocumented and no compensating detail for limit, this is adequate but not strong.

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?

The description states the exact resource (open POS identifications on the POS connection's channel), ordering (newest first), scope (only scans still within expiresAt), and payload. It is specific enough to distinguish this from sibling connection-management tools like get_pos_connection and set_pos_connection.

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?

It implies the use case with 'Who is at the till' and explains that posRef narrows to one till, plus that only unexpired scans are returned. However, it does not explicitly say when to choose this versus other listing/event tools or list exclusions, so guidance remains implied.

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