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

Annotations already declare destructive=true and idempotent=true; the description adds genuine value on top by disclosing partial-update semantics ("the fields you send" change, others are untouched) and a hard failure boundary after signing. It still doesn't say whether the token is rotated or what the call returns, which matters for a destructive mutation.

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 short sentences, both load-bearing: the first defines the mutation semantics, the second the failure condition. Nothing is wasted and the core behavior 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?

For an 11-parameter destructive legal-filing mutation with nested objects and no output schema, the description omits consequences the agent would want: whether changing classes affects pricing, whether the token survives, and what comes back. Adequate but thin against the tool's complexity.

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%, including nested owner fields and enum meanings, so the schema already carries the parameter burden. The description only reinforces partial-update behavior and adds no per-parameter detail beyond it — baseline 3 is correct.

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 (changes) and a specific resource scope (fields on a draft application), and the word "draft" separates it from create_application and get_application. It does not name a sibling alternative outright, but the partial-update framing is clear enough to select it correctly.

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?

"Fails once the owner has signed" is an explicit precondition that tells the agent when this tool will not work, which is more than most mutation tools offer. No alternative is named for the post-signing case (there is no obvious sibling), so it stops short of a 5.

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