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

Annotations already establish read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful data-scope constraints: authorised articles only, metadata/approved fields only, and explicit exclusions of secrets, contacts, and original files. It does not explain pagination behavior or response shape, but the annotation coverage lowers that burden.

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 short and front-loaded, with the key data-scope constraint immediately following the purpose. The phrase 'through the existing application' is vague and does little work, but otherwise there is little waste.

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?

Annotations cover the safety profile, and the description covers the data scope and exclusions, which is valuable for a read-only listing tool. However, with no output schema and no explanation of query/pagination parameters, and no differentiation from get_knowledge_article, it is only minimally complete for correct invocation.

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?

All three parameters have 0% schema description coverage, and the description never mentions query, limit, or offset. An agent must infer what the query searches, whether limit is a page size, and how offset pagination works. The description adds no parameter semantics beyond the schema's conventional names and defaults.

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: reading authorised knowledge articles. It also bounds the returned data to metadata/approved fields and excludes secrets, contacts, and original files. However, it does not distinguish this list operation from the sibling get_knowledge_article.

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?

There is no guidance on when to use this list tool versus get_knowledge_article or other knowledge-related tools. It also gives no context for querying, pagination, or expected use cases beyond reading authorised articles.

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