Read Many Files

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

The readOnlyHint annotation already declares this as a read operation, so the safety profile is covered. The description adds useful context: 'Returns bounded per-file previews' and mentions context overrides exist (max_total_chars, max_files_per_task, max_lines_per_file). However, it leaves unspecified what 'bounded' means concretely or what happens when limits are exceeded (truncation? error? partial content?). The description adds some value beyond annotations but doesn't fully characterize the behavior.

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?

Two sentences, zero filler. The first sentence states purpose and motivation, the second clarifies the return behavior. Every word earns its place, and the critical distinction (batching) is front-loaded.

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?

Has an output schema and readOnlyHint annotation, which lighten the burden. The description covers the core purpose and return behavior but doesn't address limit semantics (what happens at bounds), whether files can be non-text, missing-file handling, or the interaction between per-file and total limits. For a tool with 7 parameters and 50-file batches, some edge-case guidance would improve completeness, but given the output schema and annotation coverage, this is adequate.

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 71%, and the description doesn't add parameter-level detail beyond what the schema provides. The 'files' array parameter's structure (path, start_line, end_line, max_bytes) is entirely schema-documented. 'Bounded per-file previews' hints at the max_bytes/max_chars semantics but doesn't explain the preview behavior specifically. The description mostly relies on the schema, which is baseline-acceptable at this coverage level.

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?

Clear verb+resource: 'Read multiple text files in one compact tool call.' It distinguishes from the sibling 'read' tool by emphasizing the batching benefit ('reduce repeated read/cat windows'). However, it doesn't explicitly distinguish from other reads like 'read_rule_summary' or 'read_acceptance_result', and the distinction from sibling 'read' is only implied through the batching rationale rather than stated directly.

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 implies when to use it: when you need to read multiple files at once ('reduce repeated read/cat windows'). But it doesn't explicitly state when NOT to use it (e.g., single file reads, non-text files, binary files) or name alternative tools. With 32+ siblings including 'read', 'tree', and 'search_project', explicit exclusion guidance would materially help an agent decide between them.

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