ask_atlas

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

With no annotations provided, the description carries the full burden, and it delivers: it discloses single-turn behavior, API key requirements (ASK_FABLE_ATLAS_API_KEY or ATLASCLOUD_API_KEY), local-CLI auto-routing for Grok models, HTTP for others, free model-catalog calls, and refusal domains. It also states that broad conceptual engineering questions are fine while offensive-security and non-software domain asks are refused.

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 the length is largely justified by the tool's routing complexity, auth requirements, and sibling relationships. Core purpose is front-loaded and each sentence carries distinct operational information; however, the density and extended routing details make it slightly harder to scan quickly.

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?

Despite having no output schema and five parameters to contextualize, the description is operationally complete: it covers model selection flow, effort behavior, context usage, auth requirements, cross-tool token syntax, refusal policies, and single-turn semantics. An agent gets enough guidance to invoke the tool correctly and route around alternatives.

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%, but the description adds substantial meaning beyond the schema: it gives concrete model examples, explains the effort parameter's token-budget and reasoning_effort mapping, clarifies the default when model is omitted, and advises passing context for questions about existing code. This exceeds the baseline expected from schema-only documentation.

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 opens with a specific verb, resource, and scope: 'Ask a single Atlas Cloud text model — on its own — to reason about the SOFTWARE/ENGINEERING work you're doing.' It also names the behavioral boundary that separates it from siblings like ask_council, ask_chain, and ask_debate ('single', 'on its own'), making the tool's identity clear.

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, actionable routing: 'REACH FOR THIS the first time an Atlas model is wanted: call list_atlas_models... then call ask_atlas', and it explicitly prefers ask_grok for Grok models when the local CLI exists. It also clarifies when to use sibling multi-model tools via dynamic atlas:<model> tokens, providing both positive and negative selection criteria.

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