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

No annotations are supplied, so the description carries the full burden. It usefully discloses the consequential behavior of "full" mode (retiring listings not present in the payload) and the 200-row cap, but leaves unexplained what "retire" actually means (delete vs hide), auth/permission requirements, and what happens on partial failure — all material for a bulk mutation.

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?

Three tight clauses, front-loaded with the operation and the key, followed by mode semantics and the size limit. No filler and nothing that needs to be re-read.

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 bulk upsert with no annotations, no output schema, and a nested item object of ten fields, the description covers the top-level contract but not the payload's field semantics or the result shape. An agent can call it, but cannot confidently predict what happens to rows it omits or what a mixed-outcome response looks like.

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?

Top-level schema description coverage is 0%, so the description must compensate, and it does add real meaning for "mode" and for externalId as the upsert identity key, plus the 200-row limit. It says nothing about the nested listing fields (status, district, description, condition) or whether matching externalId causes merge or replace, which is the critical semantic gap.

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 a specific verb and resource ("Upsert the catalogue") and identifies the identity key (externalId), which is precisely the information an agent needs to distinguish it from create/update-style siblings. It never names a sibling such as bulk_create_listings, so the differentiation is implicit rather than explicit.

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 gives clear in-tool guidance for choosing mode: "partial" touches only sent rows, "full" retires listings absent from the payload. However, it offers no guidance on when to use this bulk upsert versus bulk_create_listings, update_listing, or set_listing_status, so alternative selection 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.