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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds value beyond annotations by specifying the return content ('collection names, ages, and PBDB occurrence counts') and the data source, auth status, and licensing ('macrostrat.org/api/v2, no auth required, CC BY 4.0'). No contradiction with 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?

Three sentences, each earning its place: the first states the core action and lookup mechanism, the second the return fields, and the third data source/auth/licensing. Information is front-loaded and there is no filler or repetition of schema details.

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?

For a 3-parameter read-only tool with an output schema and safety annotations, the description covers the essential decision points: ID provenance, optional interval narrowing, return content, data source, and auth/licensing. Minor gap: it does not clarify behavior if both col_id and unit_id are supplied (or neither), but this is a small omission given the other supportive structures.

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%, and each parameter in the schema already carries descriptive text, including the source tools for col_id/unit_id and the optional nature of interval_name. The tool description mostly restates this information ('looked up by col_id or unit_id (from macrostrat.columns_search / macrostrat.units_search)'), adding little beyond the schema baseline.

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 ('Get') and resource ('Paleobiology Database (PBDB) fossil collections'), and clearly states the scope: matched to a Macrostrat stratigraphic column or rock unit. It also distinguishes this tool from its siblings (columns_search, units_search, map_units) by focusing on fossils and the PBDB, making 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 explicitly tells the agent where to obtain the required IDs ('from macrostrat.columns_search / macrostrat.units_search'), effectively routing usage after those sibling tools. It also explains the optional narrowing by interval_name. It stops short of an explicit 'when not to use' or alternative-fossil-search guidance, but the contextual flow is strong.

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