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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds significant detail: batch limits, independent per-file errors, a cumulative byte cap (8388608 bytes), and the error code BATCH_BUDGET_EXCEEDED. No contradictions with annotations.

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?

Three concise sentences, front-loaded with the core purpose. Every sentence adds essential information about constraints and behavior. No redundancy or unnecessary words.

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 the 4 parameters, 0% schema description coverage, and existing output schema, the description covers batch behavior well but omits parameter explanations (e.g., what 'siteId' or 'maxBytesPerFile' do). Lacks completeness for parameter semantics.

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 0%, so the description must compensate. However, it only implicitly references the 'paths' array (via 'up to 50 paths') and a cumulative cap (related to overall bytes). It does not explain 'siteId', 'maxBytesPerFile', or 'name' parameters, leaving significant gaps.

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 the tool performs a batched read of source files, with specific limits (up to 50 paths) and error handling (independent failures). This distinguishes it from siblings like read_file (single file) and read_files (likely broader scope).

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 use for batched reads of the editable source tree but does not explicitly state when to use this tool versus alternatives like read_source_file or read_files. No exclusions or alternative recommendations are provided.

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