Read Multiple Files

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

The description goes beyond annotations by stating 'Failed reads for individual files won't stop the entire operation,' which is a key behavioral trait. It also confirms 'Only works within allowed directories,' consistent with openWorldHint=false. While annotations already provide readOnlyHint=true and openWorldHint=false, the description adds useful detail about partial failures and return format, enhancing transparency without contradiction.

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 consists of four clear sentences that front-load the core purpose and progressively add efficiency, partial failure, and scope details. Each sentence adds value and there is no redundant or extraneous text. Could be slightly more compact by merging the last two sentences, but overall it is well-structured and efficient.

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 tool with one parameter, annotations, and an output schema, the description covers the essential context: purpose, efficiency, partial failure behavior, and directory restriction. Minor gaps exist (e.g., maximum number of paths, handling of binary vs text files). However, given the tool's simplicity, the description is largely complete and provides agent with sufficient decision-making information.

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 coverage is 100% with a clear description for the 'paths' parameter. The tool description does not add new semantic nuance beyond what the schema already provides (e.g., no additional format, constraints, or limits on the number of paths). Per scoring rules, baseline 3 applies when high coverage exists and description does not extend meaning.

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 'Read the contents of multiple files simultaneously' with a specific verb and resource. It explicitly differentiates from sibling single-file tools like filesystem__read_file by highlighting batch efficiency and stating 'more efficient than reading files one by one.' This makes the tool's purpose distinct and unambiguous.

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 clear context for when to use the tool: 'when you need to analyze or compare multiple files.' It also notes the efficiency benefit over sequential reads. However, it does not explicitly exclude scenarios where the batch approach might be inappropriate (e.g., very large file sets) nor name alternative tools (e.g., filesystem__read_file) as direct exclusions. Overall, usage guidance is strong but lacks explicit when-not-to-use.

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