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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely non-structured behavior: results come back passage-by-passage in learning order and are capped at 50. It doesn't say whether the 50 is a hard truncation or how to page past it, which keeps it from a 5.

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 what is returned, then the usage constraint and alternatives. The parenthetical enumerating source types earns its place by clarifying what a 'source' is, though the trailing example is slightly more than strictly needed.

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 exists, and the description adequately conveys the return content and ordering, which is the main thing an agent needs. The gaps are the undocumented `workspaceId` and the unspecified truncation behavior when a source exceeds 50 passages.

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?

`source` is documented in the schema and the description reinforces the exactness requirement, but schema coverage is only 50% and `workspaceId` is described nowhere — neither in the schema nor in the description. With half the parameters undocumented, the description does not compensate for the coverage gap.

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?

States a specific verb and resource ('the text Sparky learned from one source') plus the return shape: passages in learning order, capped at 50. It names its sibling dependencies (list_knowledge_sources, delete_knowledge_source, teach_knowledge), so an agent can separate it from search_knowledge or list_knowledge_sources without opening a schema.

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?

Gives the prerequisite ('Pass the exact `source` from list_knowledge_sources') and a concrete when-to-use scenario: inspect a source before deleting it or before replacing it via teach_knowledge with `replaces`. It even supplies an example intent ('find the note with an old price'), leaving nothing to inference.

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