add_feature

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

Beyond the annotations (openWorldHint, destructiveHint), the description discloses critical behavioral traits: it populates historical data, auto-fetches metadata, takes a few seconds, auto-translates non-USD currencies and adds an FX pair, and returns a 409 for existing tickers. It also clarifies the currency exposure nuance to prevent user confusion. No contradiction with annotations; instead, it enriches them with concrete side effects and error conditions.

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 long but well-structured with bold headers for is_asset handling and currency handling. It front-loads the core action and purpose, then dives into necessary nuances. The enum lists are somewhat redundant with the schema but are presented coherently for the override case. It earns its length given the tool's complexity, though a slightly tighter delivery could improve conciseness.

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 tool's complexity (12 parameters, auto-detection logic, currency conversion, and side effects), the description is remarkably complete. It covers all key usage scenarios, edge cases (existing ticker, unsupported currency), and explains the return readiness. The presence of an output schema means return values need not be detailed, and the description properly focuses on behavioral and preconditions.

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?

With 100% schema coverage, the baseline is 3, but the description adds substantial semantic meaning beyond the schema. It explains how is_asset auto-detection works, when category/sector/asset_type become required, and lists the exact allowed enum values in a consolidated context. It also clarifies how units, display_name, and other fields are auto-detected, which the schema merely mentions. This is a paradigm of description adding value over the schema.

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 the tool's purpose with a specific verb and resource: 'Add a ticker to the feature catalog AND populate its historical data in one call.' It explains the outcome (feature ready for use) and distinguishes this from search_features by requiring a check for existing tickers. Although it doesn't explicitly compare to add_features_batch, the singular 'a ticker' and the detailed single-add workflow make the purpose unmistakable.

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?

The description provides explicit usage guidance: 'First use search_features to check if the ticker already exists' and warns about 409 errors for existing tickers. It also gives source selection advice ('yahoo' vs 'fred'). However, it does not explicitly mention the batch alternative (add_features_batch) for adding multiple tickers, so it stops short of fully distinguishing from all siblings.

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