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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful behavioral nuance: matching is three-way (containing, contained, overlapping) and source-slug mode returns everything that source publishes. It does not describe response format or limits, but for a safe lookup tool this is a minor gap.

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 dense and mostly useful, but it opens with an inline JSON call to the sibling whoami tool before stating lookup_prefix's actual purpose. That makes the structure less front-loaded and potentially confusing during tool selection. The main behavioral statement is buried after an em-dash, though every other part earns its place.

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 simple two-mode lookup with no output schema, the description covers the core return semantics (matching prefixes by containment/overlap or by source) and gives an example call. It does not specify behavior when both or neither parameters are supplied, and it does not mention potential result size, but those are marginal for invoking the tool correctly.

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 coverage is 100%, so the baseline is 3 because parameter descriptions already exist in the schema. The description adds value by framing cidr and operator as mutually exclusive alternatives ('Give an operator or source slug instead') and by providing a concrete cidr example. This goes slightly beyond the schema without doing the schema's job.

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 clearly states that lookup_prefix returns all published operator prefixes that contain, are contained by, or partially overlap a given CIDR, and that it can alternatively return everything published by a source slug. This is a specific verb+resource behavior with concrete use cases. It does not explicitly differentiate this tool from sibling tools such as range_stats, so it stops short of a 5.

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 explicit use cases: checking whether a network collides with a crawler range and auditing an allowlist. It also tells the agent when to provide a CIDR versus an operator/source slug by using 'instead,' and it opens with a whoami prerequisite. It does not state when not to use this tool relative to the sibling range or verification tools, so exclusions are missing.

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