read_files

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

With no annotations provided, the description carries full responsibility. It discloses the read-only nature, absence of side effects/auth/rate limits, the return structure (per-file records, total_est_tokens, errors[]), and the non-aborting error isolation. This is thorough and exceeds typical expectations.

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 three concise sentences with no fluff. It front-loads the core purpose, then layers return details, safety, and usage guidance. Every sentence earns its place.

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 there is no output schema, the description explains the return values (per-file annotated records, total_est_tokens, errors[]) and error behavior. It also covers limitations and usage context, making it complete for a batch tool with a single parameter.

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?

Although the schema already describes `ids` as 'File IDs to read (max 200 per call)', the description adds meaningful context: the batching purpose, the aggregation of token estimates, and the paging strategy for >200 IDs. This goes beyond the schema's basic parameter description.

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 a specific verb and resource: 'Batch read up to 200 files by ID in one call.' This clearly distinguishes it from the single-file sibling `read_file` and other file-reading tools. The scope and behavior are immediately evident.

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 explicitly states when to use this tool: 'Use instead of looping read_file to halve round-trips and get the combined token cost upfront.' It also provides a constraint: 'For >200 IDs, page yourself.' This gives clear actionable guidance on when and how to use it.

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