Files that instruct the agent

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

Despite no annotations, the description discloses a critical behavioral constraint: file contents are never returned, so the agent must open paths itself. It also mentions imports resolving outside the repo, adding context beyond simple listing. This is strong disclosure for a read-only metadata 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 sentences: the first enumerates what the tool returns, the second states a key limitation. Every word contributes, and the structure is well front-loaded.

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?

With no output schema, the description must convey return values, and it does: files with size, estimated token cost, and @import lines. It also tells the agent that contents are not included. This is complete for a simple, single-parameter listing tool.

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 input schema fully describes the only parameter 'dir' with default behavior, achieving 100% coverage. The description adds no additional parameter detail, so it meets the baseline but doesn't exceed it.

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 identifies the tool's output: all instruction files (CLAUDE.md, AGENTS.md, .cursorrules, etc.) with size, token cost, and @import details. This is specific and distinct from sibling tools which cover MCP servers, summaries, commands, and extensions.

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 purpose is evident: use when you need to know which instruction files exist and their imports/costs. It doesn't explicitly state exclusions or alternatives, but the sibling tools are semantically different, making the use case clear without further guidance.

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