Search economic data series (FRED)

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

Beyond the annotations' readOnlyHint and idempotentHint, the description discloses an important behavioral wrinkle: search coverage depends on whether the server has a FRED_API_KEY and falls back to a ~50-series catalog otherwise. This conditional data-source behavior directly affects result completeness and is exactly the kind of context annotations do not provide. It also implicitly communicates that no state is mutated, consistent with destructiveHint=false.

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?

Two sentences with no filler: keyword examples up front and the behavior caveat second. Every statement earns its place and the most call-relevant information is front-loaded before conditional details. Nothing extraneous is present.

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 three simple parameters fully documented in the schema and an output-free output-free output-schema absence, the description covers the key operational context: search by keyword, scale, and API-key fallback behavior. It does not describe the result payload structure or explicit next-step guidance like using macro_get_series once an ID is found. Minor gaps; almost complete for typical keyword-search usage.

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 100%, so the schema already documents query, limit, and response_format thoroughly. The description adds realistic keyword examples for query, but the description contributes little beyond what the schema itself states. Baseline 3 is appropriate since the schema carries the parameter-semantic burden.

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 uses a specific verb and resource combo—'Find FRED series IDs by keyword'—and gives concrete example keywords, making it immediately clear this tool searches economic data series IDs. The first sentence distinguishes it from sibling retrieval tools like macro_get_series by framing this as keyword discovery of IDs. The FRED-specific framing and keyword examples leave no ambiguity about its role.

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 clearly establishes the intended use case: keyword-based discovery of FRED series IDs, with representative queries showing when an agent would pick this tool. It does not explicitly name alternatives or state when not to use it, though the sibling set of FRED retrieval tools makes the boundary mostly implicit. Without explicit when-not/alternative language, it stops one step short of a 5.

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