clients_from_registry

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds that details come from an external ANAF registry with auto-fill of name/address/VAT/registration number. It does not say what happens when the CUI is unknown or ANAF is unavailable, nor does it warn that repeat calls will create duplicate clients despite idempotentHint=false. Note also a mild tension: the description implies an external network dependency while openWorldHint is declared false.

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?

Two sentences, zero waste: the action and auto-filled field list come first, and the disambiguation rule follows. Nothing is repeated from the annotations or schema.

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?

There is no output schema, so the description is the only place to learn what a successful call yields (e.g., the created client record, or a partial record when ANAF returns nothing), and it stays silent on this. Combined with no failure-mode guidance, the definition is serviceable but leaves real gaps for a mutating, network-dependent creation tool.

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%, so all three parameters (cui, name, companyId) are already documented, including the fallback/override intent. The description reinforces that the CUI drives the lookup but adds no format, validation, or override-precedence detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 concrete verb chain (look up CUI in ANAF registry → create client) and enumerates the auto-filled fields, so the effect is unmistakable. It distinguishes itself from clients_create by name, but not from the much closer sibling clients_anaf_lookup, which an agent could easily confuse with a lookup that only resolves details.

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?

Explicit routing rule: 'Use this instead of clients_create when you only have a CUI and want the company details resolved automatically' — a clear when-to-use with a named alternative. It omits the important when-not cases: no guidance about checking for an existing client first, and no mention of clients_anaf_lookup as the read-only alternative when the caller does not actually want a client created.

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