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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real behavior: 50 results per page, the returned field set, the caveat that coverage labels do not mean local geography (I-94 example), and an obligation to repeat each figure's notice when used. That attribution requirement is the kind of usage constraint annotations cannot express.

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 what is searched and how matching works, then filters, then result shape, then the coverage caveat. Mostly efficient, though the trailing 'Facts, not investment or other advice' sits outside the tool-selection task and the notice-repetition sentence could be tighter.

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?

With no output schema, the description usefully enumerates returned fields and page size, and warns about coverage semantics — enough to call it correctly. It stops short of telling the agent how pagination terminates (page max 1000 is only in the schema) or that series_history is the follow-up for a matched id.

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 geo, source, frequency, page and query are already documented in the schema. The description adds the important matching semantics (all words must match, case/okina folding) and labels geo/source/frequency as exact filters, which is genuinely beyond the schema, but page size is the only other addition — baseline 3 with a small lift is right.

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 (find) and resource (series) plus the exact fields matched (id, title, coverage) and the matching rule (all words must match; case and ʻokina ignored). This is concrete enough that an agent can distinguish it from latest, series_history and list_sources without opening a schema.

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?

Implies usage through the 'words in id, title or coverage' + 'optional exact filters' framing, and points at list_sources for valid source ids, but never says when to choose this over latest or series_history, nor when exact filters should replace a keyword query.

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