owp_build_delivery_package

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

There are no annotations to rely on, so the description carries the burden. The description implies a read/export operation, but it's unclear if this produces a file, returns a link, or triggers a background process. The word 'build' in the name and 'Export' in the description suggest some processing might occur, but the agent is not told about side effects (e.g., does it create a persistent package? Is it idempotent?). No error conditions, permissions, or side-effect disclosures are mentioned.

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?

The description is a single, efficient sentence with no fluff. It front-loads the action ('Export') and describes the resource. Every word earns its place. However, it's so brief that it misses important information, which hurts its score below 5, but as a pure exercise in conciseness, it's well-structured.

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?

The tool has three required parameters, no annotations, no schema descriptions, and an output schema (details not shown). However, the description doesn't explain the output, the meaning of the parameters, or the context in which this tool is used. There's no mention of what happens with 'output' (is it a path? a format?), or what 'privacy_view' options exist. The description covers maybe 10% of what an agent would need to use this tool confidently. Given the complexity of the sibling tools (crypto, verification, binding), this is insufficient context.

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 0% and the description doesn't add any parameter-specific meanings. The parameters 'ledger', 'output', and 'privacy_view' have no descriptions in the schema, and the description's mention of 'public, diagnostic, or customer-private' hints at 'privacy_view' values but doesn't connect them clearly. The agent is left to guess the valid values for each parameter, the expected format (e.g., paths, URIs, enums), and how the three parameters interact. For a build tool with 0% coverage, this is a significant 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?

The description 'Export a public, diagnostic, or customer-private delivery package.' uses a clear verb ('Export') and names the resource ('delivery package'), but likely a type of package. The phrase 'public, diagnostic, or customer-private' provides some scope, though the actual difference between these package types is not explained. However, among many 'owp_' sibling tools, this one is differentiated by the verb 'build' in the name and 'Export' in the description, though alternatives like 'owp_verify_*' also involve packages. It's adequate but doesn't fully distinguish from potential sibling tools that might also deal with delivery packages.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description is a single sentence with no mention of prerequisites, when not to use, or reference to sibling tools. The list of siblings (e.g., 'owp_run_verification', 'owp_get_decision') suggests a broader workflow, but the description doesn't guide the agent on when 'build' is appropriate versus other actions. No exclusions or alternatives are mentioned.

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