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

The description advertises a delete action ('Create, update, delete, or assign layer groups'), yet annotations declare destructiveHint=false, which per the annotation semantics asserts the tool performs only additive updates. A group removal is a non-additive mutation of the project spec, so the description directly conflicts with the structured safety signal and could mislead an agent about reversibility. The otherwise-useful expectedSpecVersion/stale-write context cannot offset this contradiction.

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?

Two sentences, zero filler: the capability statement comes first and the concurrency requirement second. Each sentence carries distinct information and nothing is repeated from the title or annotations.

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 compound four-action mutation tool with nested objects and no output schema, the description is only minimally sufficient. It does not say what a stale expectedSpecVersion produces (error vs. silent retry), does not clarify what delete does to the layers inside a group, and gives no response information, though the rich nested schema and annotations cover part of the burden.

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?

Top-level schema description coverage is 0%, so the description must carry projectId, expectedSpecVersion, and the input envelope. It meaningfully explains the one non-obvious parameter, expectedSpecVersion, as an optimistic-concurrency guard against stale writes, which the schema (bare integer with min/max) does not convey; projectId is self-evident and the nested input fields (action enum, group.id/name/collapsed, layerIds) are documented inside the schema itself.

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?

Names a concrete verb set (create, update, delete, assign) and a specific resource (layer groups in a project map), so an agent can immediately tell this apart from layer-level siblings such as geobble_project_add_layer or geobble_project_reorder_layers. It stops short of explicitly contrasting itself with the closest ambiguous sibling, geobble_project_manage_context, so it is clear but not maximally differentiating.

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 four action verbs imply when to reach for this tool (group CRUD on an existing project map), and the note that expectedSpecVersion is required to prevent stale writes gives a prerequisite. However, there is no explicit when-not guidance and no routing to alternatives, e.g. whether assigning layers belongs here versus geobble_project_add_layer, leaving usage to inference.

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