Cards Compile Drafts

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

With no annotations, the description carries the full burden and does well: it discloses the deterministic transformations applied (HTML escaping, sequential cloze renumbering c1..cN, ID leak purging, markdown table conversion, pipe escaping) and what is returned. It stops short of stating failure behavior on malformed drafts or whether the operation is idempotent, which matters for a compiler.

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 tight sentences, front-loaded with the action and output, then the transformation list, then the return payload. The dense technical vocabulary earns its place, though the middle sentence could be scannable as a list rather than a run-on clause.

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?

Return values are covered by both the description and an existing output schema, so that gap is closed. The remaining shortfall is the three optional flags, which are undocumented in both schema and description for a tool whose correctness depends on whether IDs are purged and clozes renumbered.

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 clarifies the accepted forms of drafts_json (a JSON string of a list or {'cards': [...]}) and implicitly explains the renumbering and ID-purge behaviors that auto_renumber and auto_purge_ids toggle. However, it never says those behaviors are switchable, never gives their defaults, and leaves default_campo_estudo entirely undefined.

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 opens with a specific verb+resource: 'Compile a list of structured CardDraft JSON objects into AnkiMBR-compliant QA and Cloze CSV blocks', and enumerates the transformations applied. An agent can distinguish this from a generic CSV builder, though no sibling (e.g., csv_build_row, export_final) is named to sharpen the boundary.

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?

It describes what the tool does but never states when to reach for it versus the nearby csv_build_row or export_final tools, nor any preconditions (e.g., drafts must already be validated or quarantined). The only guidance is about accepted input shapes, which is parameter-level, not usage-level.

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