bulk_read

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

With no annotations provided, the description carries the full burden. It meaningfully discloses that the tool delegates summarization to a worker LLM and that it returns the worker summary, never raw file content. While it doesn't cover auth or error behavior, the key transformation and output characteristics are clearly stated.

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 sentences with zero filler. The core behavior and usage guidance are front-loaded, followed by the return-value caveat. Every sentence earns its place and the description is appropriately sized for the tool's simplicity.

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?

For a tool with no output schema alerts and no sibling list, the description covers the essential aspects: what it does, when to use it, and what it returns. The only notable gap is the undocumented model parameter, but that is optional and less critical, so the definition is still mostly complete.

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 0%, so the description must compensate. It gives context for 'paths' (multiple files) and 'question' (summarization context), but does not address the optional 'model' parameter at all. This is a partial but not complete compensation for the schema's lack of descriptions.

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 identifies the action ('Read multiple files'), the resource (files), and the specific behavior (asking the worker LLM to summarize them in the context of the question). It explicitly differentiates itself from the alternative 'Read' tool, so an agent can distinguish it without needing additional context.

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 provides concrete, actionable criteria: 'Use instead of `Read` for 2+ files or any file >100 lines.' This is an explicit when-to-use instruction with a named alternative trigger condition, leaving little to inference.

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