List Files

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful behavior beyond annotations: it operates on the local index, returns lightweight records, and does not load full note bodies. It does not discuss error conditions or index staleness, but those are not essential for selection.

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?

Every sentence earns its place: purpose, return characteristics, when to use, a parameter tip, and sibling routing. Information is front-loaded with the core function stated first.

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 read-only filtered list with no required parameters and full schema coverage, the description covers scope, return shape, use cases, and alternatives. No critical calling information is missing.

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 covers 100% of parameters with useful descriptions, so the baseline applies. The description adds only a mild clarification that no_metadata targets Markdown files without YAML frontmatter, not enough to meaningfully surpass the schema.

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?

States a specific verb and resource: 'List notes already known to the local index.' It explicitly lists returned record fields (path, type, level, sign) and distinguishes itself from graph-traversal siblings by directing agents to get_children or get_parents.

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?

Gives explicit use cases ('inventory, filtering, and finding files to inspect next'), a specific filter recommendation (no_metadata=true for Markdown files without YAML), and names alternatives for graph traversal. An agent knows exactly when to choose this tool.

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