inventory

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

With no annotations, the description carries the full behavioral burden, and it states a non-obvious behavior: persistence is server-computed and must not be derived from first_seen. It also enumerates the classification values, giving the agent a concrete picture of what the tool will return.

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 tight and front-loaded: the purpose appears in the first sentence, the key output detail is bolded, and the warning sentence prevents a likely misuse. No filler.

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?

A basic call with only the required asn is feasible, and the return shape is described. However, the optional parameters are undocumented and there is no output schema, so an agent cannot confidently craft richer queries or interpret edge cases.

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 20%, and the description adds no parameter guidance. start/end, classify, and min_prefix_len are left to name-guessing; the agent cannot tell what date range means, how classify affects output, or how min_prefix_len filters.

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 concrete question ('What does this ASN announce...') and then states a specific deliverable: each prefix plus a server-computed persistence classification. It distinguishes the tool from first_seen-based inference, but it does not explicitly differentiate from sibling tools like timeline or origin_history.

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 instruction 'Do not infer persistence from first_seen — use this' gives a clear directive on when to rely on this tool. It identifies the use case for persistence classification, though it does not name sibling tools or specify when not to use inventory.

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