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

Annotations only supply readOnlyHint=true, but the description adds the full response contract (field names, observation: 'latest_only'), the failure/refusal shape with refusal_reason and licensor, the enumeration of refused third-party series, the restricted keyed-posture note, and that caveats ride in tool_notes. This is unusually rich behavioral disclosure.

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 the core purpose and return shape before detailing refusals. The enumerated list of seven licensed series is long but each entry is functional, and there is little filler prose.

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?

There is no output schema, yet the description fully specifies both the success payload and the two error/refusal payloads, plus licensing and posture constraints. Nothing an agent needs to call 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 coverage is 100%, so the baseline is 3; the description goes further by naming concrete FRED ids that are accepted (GDP, UNRATE style) and, more usefully, ids that will be rejected, which tells the agent how to interpret the series argument beyond 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?

States a specific verb and resource: fetch ONE latest observation for a single FRED series from Oxford Ledge's ~41-series macro snapshot, keyed by FRED id. It explicitly scopes itself against siblings like get_bond_data and get_yield_curve by limiting to the snapshot and to 'latest_only, never a history'.

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 tells the agent the operating conditions clearly: only snapshot series work, out-of-snapshot ids error, and a named set of licensed series are refused with a reason. It does not explicitly route to an alternative tool for history or full FRED access, so it stops 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.