bundle_search

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

The description explicitly states the tool is read-only with no side effects, auth, or rate limits. It details the budget algorithm: files added in rank order until the next would exceed, with remainder in `skipped[]`. This fully compensates for the absence of 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?

The description is a single, well-structured paragraph that front-loads the core purpose, then provides key details (budget logic, read-only nature, usage recommendation, defaults, and parameter specifics). Every sentence earns its place without redundancy.

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?

The description covers the tool's functionality well, including the output format (XML <document> blocks or markdown headers + fences) and the skipped array. However, it does not explicitly specify the exact structure of the returned bundle or skipped list, which could be helpful. Given no output schema, a bit more detail on return format would improve completeness.

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?

With 100% schema description coverage, the baseline is 3. The description adds value by explaining the token budget logic, the behavior of `project_id: null` (KB only), and the tag matching requirement (ALL must match), which go beyond the schema's descriptions. However, individual parameter details are largely covered by the schema.

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's purpose: running an FTS search and concatenating matched bodies into a single prompt-ready bundle, with specific format options (XML or markdown) and a token budget. It differentiates from siblings like `search` and `read_file` by explicitly recommending this tool when several related files are needed as one context blob.

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 explicit guidance: 'Use instead of `search` + N×`read_file` when you need several related files as one context blob.' It also clarifies defaults (format=xml, max_tokens=50000) and constraints (project_id: null = KB only; tags[] requires ALL to match), helping the agent decide when and how to use the tool.

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