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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description adds valuable context beyond those: no authentication required, Open Government Licence, the 1:625,000 scale, and the specific return fields. It does not contradict the annotations, though it does not surface the full-coverage behavior implied by optional coordinates.

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 compact and front-loaded with the core action and output types. The data-source/licence sentence earns its place. There is minor redundancy between the first and second sentences (lithology vs rock composition, rock unit name vs lexicon name, geological age range vs time period), but not enough to dilute clarity.

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?

The description is reasonably complete given the rich schema (100% parameter coverage), output schema, and safety annotations. It covers geographic scope, data source, licence, auth, and return content. The main gap is not mentioning that omitting both lat/lng returns full Great Britain coverage, though that is documented in the schema.

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 all four parameters (lat, lng, limit, radius_km) are already documented with ranges, defaults, and pairing requirements. The description adds no parameter-specific nuance beyond what the schema provides; its output-field detail relates to the result rather than to input semantics.

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 names a specific action ('look up'), a specific resource ('bedrock geology... near a point in Great Britain'), and concrete output fields (lexicon name, rock composition, time period). The BGS 1:625,000 map basis and the bedrock focus clearly distinguish it from sibling tools like borehole_search and the hazards tools.

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 gives clear context: it is for point-based bedrock geology lookups in Great Britain, and it names the geographic scope and data source. It does not explicitly mention alternatives or exclusions, and it omits the schema-supported full-Great-Britain mode when coordinates are omitted, but the primary use case is unambiguous.

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