learning_history

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description's 'Inspect' is consistent with a read-only operation. It adds useful context about the contents of returned observations, but does not disclose ordering, pagination, or any additional behavioral details. No contradiction exists.

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 a single sentence front-loaded with the verb and resource, with no filler. Each listed item earns its place and partially compensates for the missing output schema.

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 read-only listing with optional filters and no output schema, the description is incomplete: it does not state what 'bounded' means, what limit bounds, how status and target filters behave, or how results are ordered. The enums in the schema help, but parameter semantics and behavioral details remain ambiguous.

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 0%, so the description carries the burden of explaining limit, status, and target. It mentions 'target' and 'promotion status' as output fields, weakly hinting at two filters, but never explains the limit parameter, the meaning of the enums, or that these values act as filters. An agent cannot reliably infer parameter semantics.

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 the specific verb 'Inspect' and names the resource ('learning observations and candidates'), then lists the returned aspects: evidence, target, confidence, and promotion status. This makes it clearly distinguishable from mutating siblings like learning_promote and learning_rollback, and from learning_observe.

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?

No guidance is given on when to use learning_history versus learning_observe, learning_promote, or learning_rollback. The description only states what the tool does, not when it should be chosen or when an alternative is more appropriate.

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