train_deliverable

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

With no annotations provided, the description carries the full burden. It discloses that generate produces a zip + manifest + HMAC signature and that verify checks integrity and environment compatibility, which is useful. However, it doesn't disclose side effects (e.g., whether generate writes files to disk, whether verify mutates anything, whether HMAC signing requires secrets/credentials, or what happens on failure). The description is moderately transparent but incomplete for a tool that creates signed artifacts.

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 dense sentence that front-loads the core action (generate/verify) and enumerates the package contents efficiently. It packs a lot of information without redundancy. The only minor issue is that the Chinese phrasing is somewhat compressed, but it earns its place and is appropriately sized for the tool's complexity.

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 6 parameters, no output schema, and no annotations. The description explains the two actions and the package contents, but it doesn't describe the return value/response format, error conditions, or prerequisites (e.g., whether a trained model must exist, whether enterprise_id must be provisioned). For a tool that generates a signed delivery package, an agent would benefit from knowing what the output looks like and what could go wrong. The description is adequate but not 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 description coverage is 100%, so the schema already documents all six parameters. The description adds context for the overall workflow (generate vs verify) but doesn't add meaning beyond the schema for individual parameters. The description mentions 'enterprise_id' indirectly via '企业收包侧体检' but doesn't explain the isolation dependency beyond the schema's '隔离分区依赖'. Baseline 3 is appropriate since the schema does the heavy lifting.

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 clearly states a specific verb-resource pair: 'train_deliverable' generates a five-part FDE training delivery package (zip + manifest + HMAC signature) and verifies existing packages. It distinguishes the two actions (generate/verify) and enumerates the package contents, which helps an agent understand what the tool does. However, it doesn't explicitly differentiate from sibling tools like train_report or fde_compose, so it's clear but not fully sibling-differentiated.

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 implies usage: generate creates a delivery package, verify checks an existing package. The schema further clarifies that verify requires zip_path. However, there is no explicit guidance on when to choose this tool over alternatives like train_report, train_status, or fde_compose, and no mention of prerequisites or context (e.g., when a delivery package is needed vs. a simple report).

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