read_multiple_files

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

With no annotations, the description fully discloses behavior: return format (header with path and byte count), error handling (inline, non-blocking), accepted path types (absolute, file://, workspace-relative), binary file skipping, and the 200 KiB cap. This gives the agent a complete picture of what to expect.

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 five sentences, each adding distinct value: purpose, return format, error behavior, path types, and size cap. It is front-loaded with the core purpose and avoids redundancy with the schema.

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?

There is no output schema, so the description must explain return values; it does so by stating headers show path and byte count and errors are inline. However, it does not specify the exact container structure (e.g., array vs object) or how errors are represented in the response, which would improve completeness for an agent.

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 schema already documents the paths parameter with a description that lists the accepted path types, matching the tool description. The description adds a per-file size cap and error semantics, which are behavioral rather than parameter-format details. Since schema coverage is 100%, a baseline of 3 is appropriate; no additional parameter-specific meaning is provided.

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 opens with 'Read up to 20 files in a single call', which specifies the verb (read), the resource (multiple files), and a clear limit (20). This distinguishes it from the sibling read_file tool by explicitly targeting batch reading.

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 clearly implies when to use this tool: when you need to read multiple files efficiently and want partial failure isolation ('one unreadable file doesn't block the others'). It references read_file for the size cap, giving context, but does not explicitly say 'use read_file for a single file' or list alternative tools by name.

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