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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable behavioral context beyond annotations by explaining the snapshot-on-query semantics, the data provenance ('accumulates from when our users first resolve a domain'), and the implication that results are not a complete global DNS history.

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?

Three compact, information-dense sentences. The core behavior is front-loaded, followed by practical use cases and a key limitation. No filler or repetition of schema fields.

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?

Despite having no output schema, the description enumerates the returned fields (record_type, value, first_seen, last_seen, observation_count), which is sufficient for basic use. The main completeness gap is the unaddressed limit_per_type behavior, but overall this is a well-specified tool for a simple three-parameter query.

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 only 33%; only record_type has an inline description. The description mentions 'this domain' and 'record_type' but does not compensate for limit_per_type, which is undocumented in the schema and unmentioned in the description. The phrase 'Returns every tuple' also conflicts with the existence of limit_per_type, potentially misleading the agent about result completeness.

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 states a specific verb and resource: 'Snapshot-on-query passive-DNS view' that 'Returns every (record_type, value) tuple seen for this domain.' It clearly distinguishes itself from siblings like dns_lookup and dns_profile by emphasizing the historical, observed nature and its accumulation from /dns/lookup calls.

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 gives concrete use cases: 'detecting when A records moved or recovering historical NS/MX values,' and a clear exclusion: 'Not a global feed — accumulates from when our users first resolve a domain.' It does not explicitly name alternative sibling tools, but the context and limitations are clear enough for routing.

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