List Articles

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

Beyond the readOnlyHint annotation, the description discloses critical behavioral traits: every record contains full HTML content which is large, the API returns no total count, page_was_full is the only signal for more records, there is no documented archived filter, and the fields parameter ignores unknown names. These details are not available in the schema or annotations and are essential for correct use.

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 long but every sentence earns its place. It opens with a clear definition, then systematically covers filters, the critical fields caveat, and pagination honesty. It is front-loaded with the most important information and avoids redundancy or vague 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?

For a list tool with 11 parameters and no output schema, the description is remarkably complete. It explains the returned shape ('object with items plus pagination facts'), the lack of a total count, the absence of an archived filter, and even notes the response_format option. The description fully prepares an agent to use the tool correctly in every scenario.

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?

While the schema already covers all 11 parameters, the description adds significant meaning beyond the schema: company_id scoping and the null-selection workaround, the audit use case for enable_sharing, the published/draft distinction with the note that draft is not writable, and the performance impact of full content with guidance to pass fields. This transforms mere parameter names into actionable knowledge.

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 clearly states 'List articles in Hudu' and explains what an article is (knowledge-base document with HTML content, optional folder/company scoping). It distinguishes from sibling hudu_get_article by noting that after filtering with 'fields' you should 'fetch the body with hudu_get_article'. It also highlights specific use cases like auditing public exposure via enable_sharing, making the purpose unmistakable.

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 description gives explicit when-to-use guidance: use enable_sharing for 'what of ours is exposed publicly?', use draft for unpublished work, and use the 'fields' parameter when looking for an article rather than reading one, then fetch the body with hudu_get_article. It also explains what not to do (there is no archived filter, so archived articles cannot be selected) and how to handle global-only articles by omitting company_id and selecting on null.

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