audit_csv

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

No annotations are provided, so the description carries the full burden and does so thoroughly: fields checked, promos skipped and why, one live API call per unique card (latency cost), read-only nature ('does not write any changes back'), and a disclosed false-positive class for Subtypes formatting, plus the clean-CSV return behavior.

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?

Front-loaded with purpose and scope, then behavior, then usage. The false-positive paragraph and the 'does not write' note each earn their place, but the enumeration of checked fields plus the promos explanation is slightly verbose and could be tightened.

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?

Output schema exists, so return values needn't be documented, yet the description still conveys the report shape ('csv_value' → 'api_value', grouped by card, one-line summary when clean) and the scope of checks. For a single-param reporting tool, nothing an agent needs to invoke it correctly is missing.

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 specifies that csv_path is an absolute path to an *enriched* collection CSV, adding the precondition that the file must already be enriched (otherwise the audit is meaningless). That is meaningful beyond the bare 'string' schema, though format/syntax detail is minimal.

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?

Specific verb (audit) plus resource (an already-enriched Lorcana collection CSV) and an explicit negation of the closest sibling behavior ('a correctness check on data already in the CSV, not a re-enrichment'). An agent can distinguish this from enrich_csv without opening either schema.

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?

Gives concrete triggers (after a new set releases, after manual CSV edits, when enrichment output looks suspicious), an explicit when-not ('not as a routine step after every enrich_csv call') with the reason (per-card live fetches add latency), and names the correct remediation path (re-run enrich_csv, not hand-edit).

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