lb_search_start

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

Annotations already establish read-only and non-destructive behavior. The description adds that the operation is asynchronous and ripgrep-backed, which is useful. Still, it does not disclose how results are delivered, whether a session handle is returned, or how 'allowed directories' are enforced. These are meaningful behavioral gaps given the async lifecycle.

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?

A single, information-dense sentence with no filler. The core action, engine, scope, and asynchronous nature are front-loaded, and every word earns its place.

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 10-parameter asynchronous tool with no output schema, this description is incomplete. It does not explain what the tool returns, how to retrieve results, how cancel/read sessions work, or important parameter semantics. An agent would need substantial external inference to call this correctly and consume its outcome.

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 0%, so the description must compensate, but it explains almost none of the 10 parameters. The phrase 'filename or content' maps faintly to query_kind, and 'allowed directories' hints at search_root, but query_text, file_glob, deadline_ms, result_limit, fixed_string, case_insensitive, include_dotfiles, and context_line_count are left entirely undocumented.

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 uses a specific verb ('Start') and resource ('search'), and adds meaningful qualifiers: 'asynchronous', 'ripgrep-backed', 'filename or content', and 'inside allowed directories'. This clearly separates it from siblings like lb_search_read, lb_search_cancel, and lb_search_sessions.

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?

Usage is implied rather than explicit: starting an asynchronous search suggests that results are retrieved separately, likely via lb_search_read. However, the description never states when to prefer this over siblings, what to do after starting, or any exclusions. The role is evident from naming, but no direct guidance is given.

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