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

Annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the description adds the useful nuance that the SQL itself is read-only while an optional materialisation step creates derived datasets. However, 'read-only DuckDB SQL' sits in tension with readOnlyHint=false, and the description never resolves it explicitly (what exactly gets written, whether it is reversible, auth requirements). Some added context, but the safety picture is left partly ambiguous.

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?

One front-loaded sentence that names the verb and resource immediately and wastes no words. The em-dash capability list is dense but readable; only the materialisation clause is slightly tucked away at the end.

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, so the description should say what a preview returns and what materialisation yields (e.g. a new source identifier), and it does not. Combined with no guidance on permissions, query limits, or failure modes for a SQL-execution tool, the definition is adequate but leaves real gaps an agent must discover by trial.

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 reported as 0%, so the description is expected to compensate for the two required top-level parameters (projectId, input). It adds nothing about either: projectId is an undescribed UUID and the description never mentions the query, title, or action fields beyond the passing phrase 'optional materialisation'.

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 (run read-only SQL) against a specific resource (the project's GeoParquet data) and enumerates the operations available (filter, aggregate, join, measure). This clearly separates it from siblings like geobble_project_run_spatial_operation or geobble_project_explore_collection, which are not general SQL surfaces, so an agent can select it without opening the 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?

Usage is only implied: the description tells you it is SQL over GeoParquet, and the 'optional materialisation' phrase hints at the preview-vs-materialize choice. It never states when to prefer this tool over sibling alternatives (e.g. run_spatial_operation, explore_collection) or what prerequisites the project must meet.

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