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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, and the description still adds real behavior: it discloses that example structures are returned 'in no order' (so the agent must not read ranking into the output), that it 'Stops for sanctions-affected country links' (an input-triggered halt condition), and that output is 'General information, not advice' with named limitations. It does not cover pagination or output shape, but that is handled by the output schema.

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?

Sentences are short and mostly load-bearing (the exclusions, the sanctions stop, the not-advice disclaimer), but the opening is a choppy comma-run inventory and the phrase 'example structures in no order' is awkwardly placed, so the key scoping fact is not front-loaded. Nothing is pure filler, but the ordering makes the reader assemble the purpose from fragments.

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?

With six all-optional parameters, an output schema, and full annotation coverage of the safety profile, the description supplies the remaining essentials: scope, what it will not do, a sanctions-related halt condition, output-ordering caveat, and an advice disclaimer. The only meaningful gap is that it never says how varying archetype/markets/budget changes what comes back, which matters for a tool whose inputs are all optional.

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% across all six optional parameters, so the schema carries parameter meaning on its own; that sets the baseline at 3. The description only loosely gestures at inputs ('considerations by customer market' for markets, 'residence and citizenship options' for the mobility layer) and never explains the include_mobility toggle, archetype, budget_usd, or the citizenship/tax-residence inputs. No compensating detail beyond the schema.

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 names a concrete scope: a combined reference for someone mixing a relocation with a company-structuring question, enumerating what it covers (residence/citizenship options, per-market considerations, example structures, banking access levels, obligations checklist, adviser questions). The qualifier 'combining a move with a company question' is what separates it from single-domain siblings such as compliance_checklist or get_structuring_playbook, though those siblings are never named. It stops just short of a crisp action verb by calling itself a 'General reference'.

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?

The opening clause implies the when (combined move + company question), and 'It does not recommend a structure and does not plan for the person' usefully excludes the recommendation/planning use cases, which implicitly routes to recommend_programmes, compare_formation or plan_path. However, no sibling is named and there is no statement of prerequisites or of what an agent should do instead. The guidance is inferable rather than explicit.

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