Claude Review Files

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

No annotations are provided, so the description carries full burden. It explicitly states read-only behavior: 'read-only: it can Read, Glob, and Grep within the granted paths, and research the web, but never modifies anything'. It also explains the depth parameter's delegation behavior. This fully discloses behavioral traits.

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 four sentences, each earning its place: first sentence states purpose and read-only nature, second gives requirements, third compares to sibling, fourth gives use case. Front-loaded with key information, no filler.

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?

Given 6 parameters (2 required), no output schema, and no annotations, the description covers purpose, usage, behavioral constraints, parameter details, and examples. It addresses the tool's complexity adequately, providing enough context for an AI agent to select and invoke correctly.

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 100%, so baseline is 3. The description adds substantial meaning beyond the schema: explains 'depth' effect, 'model' override, requires 'absolute paths that exist', gives example question, and explains 'session_id' and 'workspace_dir' for continuing conversations. It enriches parameter understanding significantly.

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 the tool's purpose: 'Have Claude read and analyze specific files or directories agentically'. It specifies the verb (read and analyze) and resource (files/directories), and distinguishes from sibling tool ask_claude by noting it's better for larger scopes and verification workflows.

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 explicit context for when to use: 'Better than pasting file contents into ask_claude for anything larger than a snippet' and 'For verification workflows, this gives Claude an independent read'. It implies when not to use (small snippets) by contrasting with ask_claude. No explicit when-not list, but adequate guidance.

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