Read several files' text

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

Annotations already declare readOnlyHint and idempotentHint, but the description adds much more: 10 MB per-file limit, OCR for scans when enabled, per-file and total character caps, partial-failure isolation ('one failing file does not fail the others'), two-at-a-time concurrency, and a prompt-injection warning about untrusted content. This is exactly the behavioral context an agent needs before issuing a batch read.

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?

One front-loaded sentence states the operation, then the return shape and failure semantics, then caps and continuation, then the trust warning. Parentheticals pack format and size constraints without padding; no sentence is redundant.

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?

With no output schema present, the description supplies the full return contract ({results, totalChars}, per-file ok/text/truncated/nextOffset/ocr/error) plus failure isolation and truncation recovery. Nothing an agent needs to call it correctly or interpret results is missing.

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 defaults, bounds, and the skip-on-exhaustion behavior of maxTotalChars are already documented in the schema. The description adds the 10-file ceiling and the nextOffset continuation mechanic, which is useful but marginal; baseline 3 is appropriate when the schema carries the parameter load.

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?

States a specific verb and resource with batch scope: 'Read the text of up to 10 Drive files in one call', and anchors it to the sibling drive_read_content ('like drive_read_content for each'). Supported formats and size bounds are named, so an agent can distinguish it from a single-file read without opening the schema.

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?

Establishes the batch use case and gives a concrete fallback path: continue a truncated file with drive_read_content at offset = nextOffset. It does not explicitly say when to prefer drive_read_content or drive_search_content instead (e.g. single file, or locating a file by content), so routing guidance is implied rather than exhaustively stated.

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