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

No annotations are provided, so the description carries the full burden. It discloses the read-vs-write distinction (load flag) and notes cloud persistence behavior ('does not save to cloud'). However, it doesn't disclose what happens to unsaved local changes when load=true, error behavior for out-of-range indices, or the return structure beyond 'JSON state'.

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?

Three concise sentences, zero wasted words. Front-loads the primary action and index convention first, then the read-only default, and concludes with the load flag caveat. Highly efficient.

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?

With a 2-param schema at 100% coverage and no output schema, the description competently explains purpose, scope, and the side-effect flag. The main gap is absence of error-behavior context (e.g., what happens with invalid rel indices) and whether return is a full state dump or delta, but for a simple read tool this is reasonably complete.

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 coverage is 100%, and both parameters (rel, load) have descriptions in the schema. The tool description adds the load=true cloud-persistence caveat, which supplements the schema. Baseline 3 is appropriate since the schema already documents both parameters well and the description adds modest extra context.

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?

Description states a specific verb+resource ('Load one shared-map version') with clear indexing semantics (-1 newest, -2 previous). It differentiates from siblings: roadflow_list_versions lists versions while this loads one, and roadflow_get presumably gets the live map. Purpose is unambiguous.

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 clearly states the load-versus-view distinction: loading by relative index does not change the live map/workspace unless load=true. This provides context for when to use the tool, though it doesn't explicitly name alternative tools or specify when to prefer this over roadflow_list_versions or roadflow_get.

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