validate_announcement

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: it enumerates the distinct checks performed (ROA/max-length, IRR route objects, current announcers, registration changes) and states the three-valued verdict (clear | warn | blocked). It even explains the causal rationale for the registration check (freshly transferred space keeps the old holder's ROAs), which is genuinely informative. Minor gaps: it does not explicitly state that the tool is non-mutating (though 'pre-flight' strongly implies it) nor the exact return structure.

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?

The description is front-loaded with the core question, then proceeds through the checks and finishes with the return verdict. It is dense but every clause earns its place — including the em-dash rationale for the holder check, which adds causal context rather than padding. The single run-on sentence is slightly less scannable than it could be, but there is zero wasted verbiage.

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 tool with no annotations and no output schema, the description is notably complete: it covers the purpose, all four checks performed, the verdict values, and even the domain-specific reasoning behind the holder check. Remaining gaps are the exact return structure beyond the verdict names and explicit parameter value formats, neither of which is fatal given how much the description already conveys.

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%, so the description must compensate. It successfully gives functional meaning to all three parameters: `prefix` and `origin_asn` appear inline in the core question, and `check_holder` maps to the explained registration-change check. However, it does not specify value formats or constraints (e.g., CIDR notation for prefix, ASN integer range, type expectations), which is a meaningful gap given the schema itself provides no parameter titles or descriptions.

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 opens with a specific, answerable question ('will announcing `prefix` from `origin_asn` validate?') that names the exact verb, resource, and inputs. It then enumerates precisely what is checked (covering ROA and max-length, IRR route objects, current announcers, registration changes), which makes the tool's scope unmistakable and distinguishes it from the diverse sibling set (identify, timeline, reachability, etc.), none of which obviously overlap with validation.

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 description frames the tool as a 'pre-flight' check, which clearly signals it is meant to be run before announcing a prefix, giving strong contextual guidance on when to use it. However, it names no explicit alternatives or when-not-to-use exclusions. Among the siblings (detections, origin_history, reachability) there is no obvious competitor for this task, so it stands apart without needing explicit routing.

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