ask_decisionpen

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

With no annotations, the description must carry the full behavioral burden. It discloses that a server-side agent plus LLM answers the query and that thread_id enables multi-turn continuation, but it never mentions cost, latency, non-determinism of generated answers, or any auth/permission requirement — material omissions for an LLM-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?

Front-loaded with the decisive 'LAST RESORT' framing and then the fallback routing, followed by compact per-parameter lines. The fragmented note style and stray arrow chain are slightly informal but no sentence is wasted.

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?

An output schema exists, so return values need no explanation, and all three parameters plus the routing rule are covered. However, for an LLM-backed last-resort tool with zero annotations, the absence of any cost, latency, or answer-reliability note leaves a real gap.

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 0%, so the description must define the parameters, and it does explain all three: query as a natural-language question, thread_id as an optional continuation handle, and skill_id as an optional skill sourced from list_ask_skills. It stops short of describing how skill_id alters behavior or any query formatting limits.

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?

Names a specific verb+resource (narrative ask over DecisionPen, backed by a server-side agent and LLM) and explicitly frames its role as LAST RESORT, which separates it from the structured Context tools listed in the sibling set.

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?

Gives an explicit precedence chain (search_entities → relationships → get_entity_evidence / search_evidence) and states the exclusive condition for using this tool: 'only when those are insufficient.' Both when-to-use and when-not-to-use are covered.

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