exclude_paths

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses the session-only nature and reset-on-restart behavior, which is valuable context. However, it does not state whether patterns are appended to existing exclusions, whether exclusions affect the current index immediately, or any matching limitations.

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 concise and front-loaded, with the first sentence stating the action and scope. The glob examples are compact and the session-only note is a single line, with no redundant or filler content. Every sentence 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 single-parameter tool with no output schema, the description is adequate, covering purpose, syntax, and lifecycle. It lacks explicit guidance on interaction with sibling tools like include_paths or how exclusions apply to an ongoing indexing session, but the core usage is well covered and the tool is simple.

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?

The schema already documents the 'patterns' parameter with 100% coverage, but the description enriches understanding by explaining glob syntax with concrete examples ('node_modules', '*.test.py', 'vendor/**'). This clarifies how patterns are interpreted beyond the schema's generic description, adding meaningful semantic detail.

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 'Add paths to exclude from indexing (session-only)' with a specific verb and resource. The session-only qualifier distinguishes it from persistent configuration, and the sibling tool 'include_paths' makes the opposite purpose, so this tool's role is unambiguous.

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?

The description provides practical usage context with glob syntax examples, clearly implying when to use this tool (to exclude paths from indexing). However, it does not explicitly compare to alternative tools like include_paths or mention when not to use it, preventing a top score.

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