Preview Directory

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the output nature (orientation summary, ~3-5k tokens, call-graph map) and scopes the tool to broad orientation rather than targeted queries. It does not mention side effects, read-only behavior, or how the tool behaves with atypical inputs, but the output and scope are reasonably transparent.

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 short and mostly front-loaded, and it includes a useful shell invocation plus fallback command. However, the opening sentence is syntactically confusing ('No command on a directory') and the relation to 'scan' is cryptic. The content earns its place, but the phrasing weakens the structure.

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?

The core use case and output shape are described, but the tool has five parameters, no output schema, and no annotations. An agent cannot determine how to use or interpret depth, max_files, max_entries, or respect_gitignore. The missing parameter context makes the description incomplete for reliable invocation.

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%, and the description essentially compensates for none of the five parameters. The only parameter hinted at is 'directory' via the shell example 'sct <dir>'; depth, max_files, max_entries, and respect_gitignore are entirely unexplained. This is a substantial gap for an agent trying to invoke the tool correctly.

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 purpose: it provides an orientation-level overview of a directory, including size, language mix, entry points, hot functions, and a call-graph map. It also distinguishes this from the file-tree-level 'scan' tool. However, the opening phrase 'No command on a directory' is garbled and obscures the intended meaning.

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?

It states the intended use case: first-time orientation over an unknown codebase, and explicitly says it is not for targeted questions. It also positions 'scan' as the tier below for file trees. It does not enumerate sibling alternatives or give precise when-not-to-use conditions for each sibling, but it offers enough routing guidance.

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