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

Annotations already cover readOnly=false, idempotent=false, and destructive=false. The description adds useful behavior: it creates drafts (not final reports), returns IDs for review, and groups all orders under a single project. This goes beyond the annotations without contradicting them.

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 tight sentences, each earning its place: the action, the output/usage intent, and the critical single-project constraint. The most important information is front-loaded.

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?

Given the large schema and existing output schema, the description covers the key operational points: draft creation, review-before-submission, and per-project grouping. It misses nothing essential for an agent to call the tool correctly, though it could optionally mention the review path via smi_get_deep_report.

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 only 50%: projectId is well described in the schema, but the required orders parameter has no schema-level description. The tool description only says 'subject orders', providing minimal semantics for a complex array parameter. With half of parameters undocumented, the description should compensate more than it does.

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 states a specific action ('Creates one or more SMI deep report drafts from subject orders'), identifies the resource (deep report drafts), and clarifies the output ('Returns the draft ids for review before submission'). This clearly distinguishes it from siblings like smi_submit_deep_reports (submission) and smi_get_deep_report (retrieval).

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 clear usage context: create drafts first, review their IDs before submission, and group all orders under one project per call ('call once per project'). It does not explicitly name alternative tools or state when not to use it, but the draft-before-submission workflow is clearly implied.

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