unbounded_consumption_auditor__scan_directory

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

With no annotations, the description carries the full burden and only discloses that traversal is recursive. It does not state that the operation is read-only/non-destructive, how it behaves with the include/exclude/maxFiles limits, whether large trees are truncated, or what the scan produces.

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?

A single front-loaded sentence with the resource and the target anti-pattern class first and zero filler. Nothing is wasted or buried.

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 moderate-complexity directory scanner with fully documented params and no output schema, the description covers purpose adequately. However, it omits sibling routing and any notion of what findings or summary a scan yields, leaving gaps an agent must fill by inference.

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 path, exclude, include, and maxFiles are already documented in the schema. The description adds no parameter-level meaning (e.g., precedence between include and exclude), so the baseline 3 applies.

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 (recursively scan) and resource (directory of LLM/agent application source) plus the exact class of issue sought (Unbounded Consumption / denial-of-wallet anti-patterns). It implicitly distinguishes itself from the same auditor's scan_file/scan_text siblings via the directory scope, though it never names them.

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 word 'directory' and 'recursively' imply usage for whole-tree sweeps versus scan_file/scan_text, but there is no explicit when-to-use/when-not guidance or reference to alternatives. The agent must infer the choice from the tool name.

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