acm_audit

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

Without annotations, the description carries the full burden. It discloses that the untagged mode auto-tags high-confidence notes, implying a write operation. It also mentions pagination for untagged. However, it does not explicitly state if other modes are read-only.

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 well-structured: a brief overview, then a bulleted list of modes, followed by an Args list. It is concise yet informative, with every part contributing to understanding. The Spanish language is appropriate for the context.

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 complexity (8 parameters, 3 modes) and no annotations, the description covers modes and parameter constraints well. However, it lacks details on return values beyond pagination for untagged mode. The presence of an output schema partially compensates, but the description could better explain what each mode returns (e.g., clusters for duplicates).

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. The Args section adds meaning for each parameter, specifying which mode each applies to (e.g., days for recent, include_registry for duplicates, limit/offset for untagged). It explains defaults and usage, significantly adding value over the schema's bare titles.

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 it audits an Anki deck with three modes, explaining each mode's purpose. It distinguishes from sibling tools by naming the modes and referencing internal identifiers (RF-F1), but does not directly compare to alternatives.

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?

Each mode has a usage context: duplicates for dedup cross-deck, recent for reviewing recently added cards, untagged for missing taxonomies. It provides guidance on when to use each mode but lacks explicit exclusions or comparisons to sibling tools.

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