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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description goes well beyond them: it states no filing/reservation/payment occurs, explains register read-freshness via `loaded_at`, defines the `not_checked` vs `no_live_match` distinction, and warns that `no_live_match` is a positive signal, not clearance. It also adds a quoting requirement for `notice` and an explicit rule never to call a name clear unless checked in-conversation and read today or yesterday.

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?

Front-loaded with purpose and the no-side-effects guarantee, then parameters, then interpretation rules. It is dense but every clause is load-bearing; the only soft spot is the long walkthrough of return fields (`verdict`, `exact_live_mark`, `similar_live_marks`, `conflicts`, `registers`) when an output schema already exists.

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 four-parameter read tool with full schema coverage, annotations and an output schema, the definition supplies exactly the missing layer: how to interpret `verdict` values and freshness, and the safety/legal caveats. An agent can call it and report results correctly without further inference.

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 four parameters are already documented with examples and enums. The description restates them ('goods free text, mapped to Nice classes', 'classes 1 to 45', 'registers a subset... all three by default') and adds only the framing that they 'narrow the check', which is marginal 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?

States a specific verb and resource ('Read-only trademark check for ONE proposed name') plus the data source (Open Trademarks) and register coverage (US, EU, IL). It explicitly carves out what it does NOT do ('Nothing is filed, reserved, watched or paid for'), which separates it from any filing-oriented tool an agent might imagine.

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?

Gives an explicit trigger ('when the user is choosing or vetting a name for a brand, product or business') and names both alternatives with their conditions: `search_domains` for domain availability/cost and `check_domain_transfer` for moving an owned domain. The exclusion 'It checks trademarks only' closes the ambiguity.

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