Get knowledge articles

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so safety is covered. The description adds only a return type and an error section, and that error section is stale/misleading: it claims "raises MissingParameterError: If table is not provided" even though no table parameter exists and the schema has zero required parameters. The misleading error claim negates the small value of the return-type note.

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 one-line summary is front-loaded and the docstring param list is scannable, but the paired ":param" / ":type" lines are redundant boilerplate that restates types already implied by the schema. Structure is conventional and reasonably sized, yet much of the content is stale rather than wasteful-per-se.

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 12-parameter tool with no output schema and 0% schema coverage, the description should be the primary contract, but it covers roughly a third of the real parameters and misstates the error behavior. Only the brief return-type note is genuinely additive; an agent cannot correctly construct a call from this definition alone.

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 full burden — yet it documents parameters (filter, sysparm_query_category, kb, language) that do not exist in the schema, and omits eight real parameters (textSearch, api_parameters, article_sys_id, name_value_pairs, attachment_sys_id, sysparm_search_id, sysparm_search_rank, sysparm_update_view). Since the schema forbids additional properties, an agent following this description would attempt calls that fail outright.

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?

"Get all Knowledge Base articles" gives a clear verb and resource, but "all" conflicts with the presence of sysparm_limit/sysparm_offset, and it never distinguishes itself from close siblings like servicenow_get_knowledge_article, servicenow_get_featured_knowledge_article, or servicenow_get_most_viewed_knowledge_articles. The purpose is understandable but not discriminating.

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 when-to-use guidance whatsoever: nothing says when to prefer this plural list tool over the singular servicenow_get_knowledge_article or the curated most-viewed/featured variants. No prerequisites, no note about whether filtering is required or optional.

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