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

With no annotations, the description carries the full burden. It usefully discloses the three match heuristics, which is real behavioral information, but omits whether this is a read-only scan or a mutation, whether it operates on the whole shop or one customer, how match confidence is ranked, and roughly what comes back. For a dedup tool whose output likely feeds a merge decision, that is a substantial gap.

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?

A single front-loaded sentence that enumerates the match criteria with no filler. It is efficient, though the brevity comes at the cost of the missing scoping detail rather than because the tool is simple.

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, no annotations, and 0% schema coverage means the description is the only information source, and it does not cover the optional customer_id, the return shape (list of groups? per-customer matches?), or the scan scope. For a two-parameter tool with zero structured documentation, this leaves too much for the agent to guess.

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 0% and the description mentions neither parameter. 'In a shop' weakly implies shop_id, but customer_id is completely undocumented in both schema and description — an agent cannot tell whether passing it narrows the scan to one customer's duplicates or filters results some other way. The mismatch threshold behind 'likely' is also undefined.

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?

Names a specific resource (duplicate customers) and states the matching criteria used — same email, same phone digits, same name — which distinguishes it from customers_search and customers_merge in the sibling list. It falls short of 5 because it never clarifies whether the tool scans the whole shop for duplicate groups or evaluates one customer against the rest, which is the core ambiguity an agent needs resolved.

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?

There is no when-to-use guidance, no prerequisites, and no mention of the obvious follow-on sibling customers_merge, which is the whole reason an agent would call this. Usage is only inferable from the name. The description also gives no signal about when to supply customer_id versus omitting it.

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