dns.hijackcheck

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

With no annotations, the description carries full behavioral burden and falls well short. It does not say whether the check is read-only, what domains are tested and how many, which DoH endpoint is used, whether it makes external network calls (relevant for sandboxed/offline agents), or what a 'Finding' object contains. The single declared behavior -- mismatch produces a Finding -- is the only disclosure.

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?

It is short and front-loads the mechanism, but 'Killer check' is filler that consumes the opening position, and 'DoH' is never expanded. The compression costs more clarity than it saves tokens.

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?

No output schema and no annotations means the description is the only documentation, and it omits the input universe (which domains), the execution model (external DoH lookups), and the shape of the Finding result. For a network diagnostic that may fail in restricted environments, that is a substantial gap.

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?

Zero parameters, so the schema-driven baseline of 4 applies; there is nothing for the description to clarify beyond confirming the tool is parameterless and fully automatic.

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 does convey the core mechanic: compare answers from the system resolver against a trusted DoH resolver and emit a Finding on mismatch. However, 'Killer check' is unexplained jargon and neither the set of 'known-good domains' nor the term 'Finding' is defined, so the agent must guess at scope and output. It is distinguishable from dns.lookup in spirit but not stated in terms an agent can act on confidently.

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?

There is no indication of when to run this versus dns.lookup, dns.propagation, or dns.resolvers, all of which touch similar territory. No prerequisites, no exclusions, no note about whether this requires outbound DoH access.

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