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

Annotations already declare destructive, non-read-only, idempotent behavior, but the description adds real context beyond them: the mutation is scoped ('Other allocations remain'), invoice amounts are untouched, and the confirmation token is single-use with staleness invalidation. That is exactly the kind of blast-radius and token-lifetime disclosure an agent needs before a destructive write.

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?

Short and front-loaded with the gating rule (preview then confirm) before the scope details. Minor redundancy: 'Requires confirmation' repeats the earlier 'after the user confirms that preview,' and the 'Prepare assigning...' sentence is awkwardly worded.

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 destructive one-parameter mutation with annotations and no output schema, the description covers prerequisites, token handling, mutation scope, and what is not changed. Only the post-call outcome (confirmation result) is unstated, which is a small gap given there is no output schema.

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?

Only one parameter, and the schema's $defs does describe the token, but reported coverage is 0% so the description must carry weight. It does: it identifies the token's origin (preview_assign_invoice_load), its single-use nature, and the expiry/changed-record invalidation rule — semantics the schema alone does not convey.

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?

States a specific verb and resource (apply an invoice-load allocation) and names the exact upstream sibling, preview_assign_invoice_load, that produces the change. An agent can tell it apart from preview_assign_invoice_load and clear_invoice_load. The phrase 'Prepare assigning a whole invoice or exact printed-line index' is slightly muddled, which keeps it off a 5.

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?

Explicit ordering is given: call preview_assign_invoice_load, get user confirmation, then apply. It also states the exclusion condition — changed or expired records require a new preview — and that only the preview's token is accepted. No alternatives or preconditions are left to inference.

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