List directory

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety is covered. The description adds a real behavioral trait beyond them: the first output line carries the policy in force, and "list one directory" signals non-recursive scope. It stops short of permissions or error behavior, but that is a minor gap given annotation coverage.

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?

One sentence, zero filler, and the scope statement is front-loaded before the alternative-routing clauses. Every fragment 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 simple read-only, no-output-schema tool, the description covers scope, sibling routing, and a notable return characteristic. Only path constraints and failure behavior (e.g. nonexistent path) are left implicit.

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% for the single required parameter, so the description must compensate; it only weakly implies the value is a directory. It gives no guidance on path format (absolute vs. relative, must be inside an allowed directory) even though a list_allowed_directories sibling exists.

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 one directory") and immediately distinguishes the operation from its nearest siblings by naming them. An agent knows this is a single-level listing, not a recursive walk or a size-annotated listing, without opening the schema.

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?

Names both alternatives with the exact condition that selects each: list_directory_with_sizes when sizes matter, directory_tree for deeper levels. This is explicit routing rather than implied usage, so the agent can pick the right sibling directly from the text.

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