My library

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered structurally; the description usefully adds that the call is "Free" and that results include purchase tx hash and date. It does not disclose what happens when nothing is owned, how large the payload can get, or any scope limit on "this node"/"this teaching key." The duplicate-purchase warning is the main genuine behavioral value added.

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?

Two sentences, front-loaded with the content inventory followed by the actionable rule, with no filler. The density is high and the "Free" note is tacked on but short. Slight cost in readability from compressed jargon phrasing.

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?

There is no output schema, and the description compensates partially by enumerating what the response contains, which is the most important return-value information. It still omits response shape, whether results are grouped, size limits, and what an empty library looks like. For a read-only one-parameter summary tool this is serviceable but not complete.

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 0% for the single optional "include" array, so the description must carry the load. It does enumerate five content categories that roughly map to the enum values (purchases, published, applied, lessons, datasets), which helps. However, it never says that "include" is the filtering parameter, that omitting it returns everything, or that at most 5 entries are allowed — and the prose labels ("teach jobs", "training sets") do not exactly match the enum strings, leaving the mapping to inference.

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 names the resource set concretely — purchases (with tx hash and date), published knowledge, applied stack, teach jobs, training sets — so an agent knows this is an ownership/inventory summary rather than a lookup of a single item. It implicitly contrasts with item-level siblings like get_knowledge and search_knowledge, though it never names them, and jargon such as "teaching key" and "the applied stack" is left unexplained.

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?

It gives an explicit trigger: "Check it before buying anything — a knowledge you already bought must never be bought twice." That is clear when-to-use guidance tied to a concrete decision. It offers no negative cases (e.g., when a targeted get_knowledge lookup is cheaper or more appropriate) and names no sibling alternative.

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