get_knowledge

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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context: it is a lookup/reference tool, not an execution tool. It describes what each mode returns (e.g., structured root cause + fix for errors, parameter contract for op-spec). It does not detail output formatting or rate limits, but for a read-only reference tool this is adequate.

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 well-structured with bullet points and front-loaded with the core purpose. It is somewhat dense but each sentence serves a purpose given the three modes. The organization keeps it scannable despite the length.

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?

With no output schema, the description correctly carries the burden of describing return values: it mentions rulebook patterns for knowledge, structured root cause + fix + example for error, and parameter contract for op-spec. Combined with the annotations and sibling context, it is complete for an AI agent to decide when and how to invoke this tool.

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 coverage is 100%, so the baseline is 3. The description adds value beyond the schema by specifying conditional requirements: topic is REQUIRED for knowledge, errorText is REQUIRED for error, and op-spec requires a topic. It also provides concrete examples of topic values, which helps the agent understand the expected input format.

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 starts with 'X++ knowledge lookup' and then clearly enumerates three distinct functions (knowledge, error, op-spec), each with specific topics. It explicitly distinguishes itself from sibling tools by noting that d365fo_file and generate_object do not ship parameters inline and that this tool provides their parameter contracts.

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 provides explicit usage timing: 'Use BEFORE generating code' for knowledge, 'Call this instead of guessing' for error diagnosis, and 'call this after picking the operation, before the call' for op-spec. It also names alternatives (d365fo_file, generate_object) and clarifies when this tool should be used relative to them.

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