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

Annotations only give the generic destructive/openWorld/idempotent profile; the description adds real context the agent could not infer: nothing is filed or charged before the owner signs, incomplete input is tolerated because 'issues lists what's left', and the response carries a review_url plus a token that must be retained. It does not explain whether repeated calls create duplicate drafts (idempotentHint=false), a meaningful gap for a create tool.

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?

Four short sentences, zero waste, front-loaded with the action and the essential safety fact (nothing filed or charged). Each sentence contributes something an agent needs: outcome, gate, validation behavior, and token retention.

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 20-parameter create tool with no output schema, the description covers the return shape (review_url plus token) and the partial-input behavior well. But it never says what the token is used for or which tool consumes it, and it doesn't address duplicate-draft risk despite idempotentHint=false — gaps an agent needs to close before a second call.

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%, so the schema already documents all 20 parameters including the enum and conditional fields. The description adds only cross-cutting semantics (all fields optional, validation surfaced via 'issues') rather than per-parameter meaning, which matches the baseline 3.

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?

Names a specific verb and resource ('Saves a draft company formation') plus the immediate outcome ('returns review_url for the owner, who checks it and signs'). The draft-versus-filing framing implicitly separates it from filing/quoting flows, but no sibling is named explicitly (e.g., quote_formation, create_application, update_formation), so it stops at 4.

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 workflow is implied ('owner checks it and signs the authorization', 'Every field is optional; issues lists what's left'), which tells the agent this is the entry point that produces a reviewable draft. However, there is no explicit when-to-use versus quote_formation or create_application, nor any stated precondition for calling it.

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