search

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

No annotations provided, so description carries full burden. Despite 17 parameters and 4 distinct behavioral modes (LLM ranking, symbol-aware, context gathering, filename search), description provides no behavioral context about performance, side effects, return structure, or auth requirements.

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?

Extremely brief (two fragments), but the root default sentence wastes space repeating schema documentation. Front-loading the action modes is efficient, though parenthetical syntax is cryptic.

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?

Severely inadequate for a 17-parameter tool with four distinct operational modes. No output schema means description should explain return values and mode selection strategy, but it provides only a terse mode list.

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%, establishing baseline 3. Description redundantly restates root's default value already documented in schema, and lists action enum values without adding semantic relationships (e.g., which parameters are valid for which actions).

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?

Lists four specific search modes (intelligent|structured|gather|filenames) which helps identify capabilities, but 'Unified search' is vague and doesn't distinguish from siblings like index_symbols, find_duplicates, or cross_file_links that also search/explore code.

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?

No guidance on when to use each action type (intelligent vs structured vs gather vs filenames) or when to choose this tool over sibling search/analysis tools. Only mentions a default parameter value.

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