Download Minute-Candle History Archive

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

Annotations indicate idempotent and non-destructive behavior, which is consistent with the description. The description adds behavioral context beyond annotations: '1 HTTP request = 1 year', 'Archives are rebuilt nightly (no current day)', and 'Years with no data are skipped and listed in the summary'. This provides useful transparency without contradicting annotations.

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 front-loaded with the main action and key differentiator. It includes all necessary details in a concise manner. Slightly longer than ideal but every sentence adds value. Could be slightly tighter but still effective.

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 there is no output schema, the description fully explains the return format (columns, CSV file), the behavior for skipped years, and the nightly rebuild constraint. For a bulk download tool with 4 parameters and no output schema, this provides comprehensive context for the agent.

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 coverage is 100% so baseline is 3. The description adds meaning by explaining the instrumentId parameter ('from find_instrument; FIGI/ticker are not accepted'), the outputPath default, and the yearFrom/yearTo usage. This goes beyond the schema descriptions.

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 a specific verb ('bulk-download') and resource ('MINUTE candles for whole years via the REST archive endpoint'). It distinguishes itself from sibling tool get_candles by noting it is 'far cheaper for long minute history', satisfying the distinction requirement.

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 provides when-to-use ('far cheaper than get_candles for long minute history'), what to do first ('Check available years first with get_history_archive_years'), and describes output format. No exclusions needed but clear context for selection.

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