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

The description explicitly discloses the most important behavioral trait beyond the sparse annotations: 'Overwrites the previous draft.' It also warns agents to 'send everything gathered so far,' clarifying that this is a whole-replacement operation, not a merge. The annotations do not cover this behavior, so the description carries meaningful weight here.

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?

Two concise, front-loaded sentences with no filler. The purpose is stated first, and the critical overwrite warning is placed immediately after, making the most important operational detail prominent.

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?

For a draft-save tool, the description covers the essential operational contract: persistence, overwrite behavior, and the need to send the full accumulated draft. An output schema exists, so return-value documentation is not required. It could be slightly more explicit about how to obtain or populate applicationId, but the schema's UUID wrapper description helps.

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?

With only 50% schema description coverage, the description adds some value by instructing 'send everything gathered so far' and clarifying overwrite semantics. However, it does not explain the applicationId parameter or the structure/content of the draft beyond that. The field names in the schema are self-explanatory, but the description does not fully compensate for the coverage 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 identifies a specific verb ('Persists'), a specific resource ('partial W-7 intake answers'/'draft'), and a clear conversational context. It also distinguishes itself from the submit-oriented sibling by emphasizing 'draft' and 'while collecting them conversationally.'

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 frames when to use the tool: during conversational intake collection, to avoid losing partial answers between sessions. It does not explicitly name alternatives like itin_submit_itin_intake or state when not to use it, but the 'draft' vs. final submission distinction is strongly implied.

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