atlas_context

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

No annotations, so the description carries the burden. It discloses key behaviors: it composes multiple data layers under a token budget, respects operator config by default, and that an explicit 'full' overrides ATLAS_CONTEXT_OPTIMIZATION. It doesn't cover error modes or resolution-failure behavior, but schema and output schema cover much of the rest.

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?

Three short paragraphs, front-loaded with the core purpose, then the primary usage directive, then the response_profile caveat. Every sentence carries information; no filler. Could be marginally tighter but is well structured.

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?

The tool is a composite context assembler with an output schema, so return values need not be explained. The description covers purpose, when to use, and the config-override behavior. Minor gap: it doesn't mention token-budget or failure behavior when a symbol can't be resolved, but against the rich schema and output schema this is largely adequate.

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 schema already documents all three parameters including the intent enum values and target resolution semantics. The description adds the meaningful operator-config relationship for response_profile, but does not explain the intent values or target format beyond what the schema provides. Baseline 3 with slight added value.

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 (assemble) and resource (task-oriented context pack) for a symbol or file, and distinguishes itself from siblings by explaining it composes neighborhood, impact radius, tests, and brief layer so the agent doesn't chain atlas_graph/atlas_brief/atlas_search.

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?

Explicitly says to use it first when the target symbol/file is already known, and the response_profile guidance gives concrete when/when-not ('use full only when requested'). It names the alternative workflow (chaining sibling tools) it replaces.

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