import_fills

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

With no annotations, the description carries the full burden and does meaningful work: it discloses the persistence location (~/.tapelog/fills.json) and that duplicates are skipped, both non-obvious behaviors implying merge-style idempotency rather than overwrite. It omits error behavior on malformed CSVs and what is returned after import.

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?

Four tight sentences, front-loaded with the supported formats and ending with storage/dedup semantics. Every clause conveys operational information; nothing is redundant.

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 4-parameter import with no annotations and no output schema, the description is nearly complete: inputs, format-specific date handling, and storage/dedup behavior are all covered. The one real gap is the undocumented 'broker' parameter and any indication of what a successful import reports back.

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 explains csv_text, file_path, and trade_date (including the YYYY-MM-DD format), but the 'broker' parameter is never mentioned despite defaulting to 'auto', leaving a meaningfully undocumented knob for ambiguous inputs.

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 ('Import executions') plus the concrete resources it accepts: DAS Trader Trades-window CSV, Robinhood activity CSV, or generic CSV with an explicit column list. This clearly separates it from the read/analysis siblings (get_stats, find_leaks, list_trades) and the destructive clear_data.

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?

Explicitly tells the agent which input channel to use (csv_text vs file_path) and gives a conditional rule for when trade_date is required ('DAS exports have no date: pass trade_date'). No explicit when-not-to-use guidance, but the format routing is unusually concrete.

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