atlas_search

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

With no annotations provided, the description fully carries the transparency burden. It discloses the hybrid search mechanism (vector + BM25, RRF fusion), default metadata-only return, two-pass pattern, token-efficiency consideration, include_content behavior, and the actionable error when the index is missing.

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 moderately sized but every sentence adds unique value, from purpose to usage to behavioral details to error handling. It is well-structured with a clear progression and imperative guidance, not wasting words.

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?

For a complex search tool with 7 parameters and an output schema, the description covers all essential aspects: what it searches, how it works, what it returns by default, how to use it in a token-efficient pattern, and what to do if the index is missing. It also integrates sibling tool context, making it self-sufficient for an agent.

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 meaningful semantics beyond the schema by explaining query input as 'natural language or exact symbols' and elaborating the default return fields and the purpose of include_content, going beyond the schema's terse descriptions.

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 clearly states the tool searches code and documents in the project's local index, establishing it as the primary search/find tool. It distinguishes itself from siblings by explicit 'FIRST tool' positioning and naming atlas_brief as the alternative for getting bearings.

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?

Explicit usage guidance is provided: use before broad file reads or grep, use atlas_brief for unfamiliar projects, and do NOT call atlas_status first. It also explains the error path related to atlas_index, giving clear when-to-use and when-not-to-use context.

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