codebase_watch

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

No annotations, so description carries burden. Discloses incremental update on start, debounced watching, and stop/status capability. Lacks side effects like resource usage or cleanup on stop, but adequate for a watch tool.

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?

Two efficient sentences, front-loaded with main action, no redundant phrases.

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?

No output schema, but description doesn't specify return values (e.g., status messages). Also no mention of prerequisites like prior indexing, though sibling tools may cover that. Some gaps for agent decision-making.

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 100%, but description adds behavioral context: action='start' triggers incremental update then watching, not just starting. Adds meaning beyond enum labels.

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?

Clearly states verb (start/stop), resource (project directory), and effect (automatically update index). Distinguishes from siblings like codebase_index (one-time index) and codebase_status (status only).

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?

Explains when to use (watch for changes) and what happens on start (incremental update then debounced watching). Lacks explicit when-not or alternatives, but context implies use when live updates needed.

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