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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description usefully explains that tension: query execution is read-only but 'materialisation of derived datasets' creates a new source, which is real added context beyond the annotations. It does not disclose cost/row limits, permission requirements, or whether materialising is persisted permanently, and openWorldHint=false/idempotentHint=false go unaddressed. Not a contradiction, but incomplete for a tool that can write.

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?

A single front-loaded sentence: operation, engine, data domain, and mode all appear before any embellishment, with no wasted clauses. It is dense to the point of being slightly compressed (two em-dash asides), but nothing repeats the title or name.

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 tool with a nested input object, a mode toggle, and no output schema, the description leaves the agent guessing what 'preview' returns (row shape? row cap? column metadata?) and what a materialised derived source looks like afterwards. The SQL dialect and data domain are covered, but return and side-effect expectations are not.

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%, and the top-level projectId has no description at all, so the description is expected to compensate — it does not. It says nothing about what projectId selects, that 'title' is required when action=materialize, or anything about the DuckDB table-naming convention, all of which are only discoverable by reading the nested 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: run read-only DuckDB SQL over the project's GeoParquet data, and enumerates the operations (filter, aggregate, join, measure) plus the optional materialisation mode. It clearly differs from configuration-style siblings like project_update_layer_style, but never contrasts itself with the nearest analytical alternatives such as project_run_spatial_operation or project_analyze_mobility.

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?

No when-to-use or when-not-to-use guidance, and no named alternatives. The only mode distinction (preview vs materialize) lives in the schema, not the description, so the agent must infer from the phrase 'optional materialisation' when to switch modes or when to reach for a different analytical tool.

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