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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the write/safety profile is covered structurally. The description adds genuinely new behavioral context: the optimistic-locking contract via expectedSpecVersion preventing stale writes. It omits the failure mode (e.g., conflict error on version mismatch), whether the reorder is atomic, and that the operation overwrites the entire existing order.

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, purpose front-loaded, followed by the one non-obvious constraint. No filler, no restating of the title, no wasted words.

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-required-parameter mutation with a nested input object and no output schema, the description covers the purpose and the concurrency guard but leaves out error/conflict behavior, permission requirements, and the destructive-replacement semantics of the full ordered list. Adequate but with clear gaps for a write tool whose annotations say idempotentHint=false.

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%, but the description supplies the single most important semantic: expectedSpecVersion exists as a stale-write guard, which the schema alone does not convey. The nested layerIds and title fields are documented in the schema, but projectId and the consequences of an incomplete layerIds list are not explained anywhere — leaving a compensating gap.

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: 'Change the draw order of layers in a project map.' This is clearly distinct from siblings like project_set_layer_visibility or project_update_layer_style, which touch other layer attributes. It does not explicitly name a sibling to disambiguate against, which keeps it from a 5.

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 one real usage condition — that expectedSpecVersion must be supplied to avoid stale writes — which tells the agent it is a concurrency-guarded mutation. However, it never says when to use this versus project_add_layer / project_remove_layers / set_layer_zoom_range, nor what happens if the caller omits or mismatches the version. Usage is implied rather than spelled out.

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