Ai Prompt

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's job is to add behavioral context — and it does: the response is shaped by the organization's persona and response rules, and knowledge-base entries are injected unless disabled. It still omits latency, cost, and whether the answer is grounded/citable, which matters for an AI-backed call.

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 tight sentences with the core behavior front-loaded, followed by usage and context guidance. The middle clause 'it answers with the organization's persona and response rules and... the knowledge base entries' is slightly run-on but still efficient.

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 must convey the return nature — and it does, describing a free-form textual answer composed from persona rules plus retrieved knowledge. Remaining gaps (answer length, citation behavior, error modes) are minor for a free-form generation 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 description coverage is 100%, so all three parameters are already documented, including removeKnowledge. The description's 'unless disabled, the knowledge base entries matching the prompt' reinforces that switch but adds little beyond the schema's own wording, matching the baseline of 3 for a fully documented schema.

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: 'Run a free-form prompt through the organization's AI' and clarifies it answers with the org's persona and response rules. This implicitly separates it from siblings like ai_draft_reply and ai_translate, but never names an alternative explicitly, so it stops short of a 5.

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?

'Use it to draft texts or answer questions from the knowledge base' gives a clear context for when to reach for this tool. It offers no exclusions or named alternatives (e.g. when to prefer ai_draft_reply or knowledge_search instead), so it lacks the explicit when-not guidance that would earn a 5.

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