load_design

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low, but the description still discloses what actually differs per call: a hull draft returns a full spec while an imported/land draft returns kind, source, current revision, coordinate frame and edit log. The named failure mode adds further context. Minor gap: it does not mention size or cost characteristics of loading a large hull spec.

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?

Purpose is front-loaded in the first clause, followed by routing, payload shape and failure mode in a tight sequence with no filler. The routing sentence is densely packed (two tools and a patch syntax in one clause) but still parses cleanly.

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?

An output schema exists, so return values need not be enumerated, yet the description still tells the agent that the payload shape branches by draft kind and which editing tools to use instead. Given one required parameter, rich annotations and a closed-world read, nothing an agent needs to call this correctly is missing.

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 the single parameter is already documented as coming from list_designs. The description only adds the constraint that an unknown name fails, which is useful but is behavioural rather than additional syntax or format detail, so the high-coverage baseline of 3 applies.

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?

Opens with a specific verb+resource ("Read a stored draft") and immediately delineates two result shapes by draft kind (hull spec vs. imported/land metadata). It names the siblings that handle the mutation path, so an agent can separate it from preview_hull, store_design, query_parts and edit_parts without opening a 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?

Gives explicit routing: to change a hull draft use preview_hull/store_design with design=name and patch, and for imported/land drafts use query_parts/edit_parts rather than a spec. It also states the failure precondition (no draft with that name), which is exactly the when-not guidance an agent needs.

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