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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds nothing beyond the endpoint string: it doesn't say whether 'reset preview' is a dry-run computation, what data it computes over, or whether it requires the lease to be in a particular accounting state. For a preview/computation endpoint, that missing semantics is significant.

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?

The opening sentence is duplicated verbatim, which is pure waste, and the remaining content is metadata boilerplate (operation ID, describe_operation pointer) rather than front-loaded purpose. Short, but under-specified rather than concise.

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?

No output schema, no annotations gap to lean on, 0% param coverage, and a nested free-form query object: this is a case where the description needed to carry real weight. It supplies none of the information an agent needs to decide to call it or interpret the preview result, deferring everything to describe_operation.

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 0%, so the description must compensate and it does not: the required `id` path param and an untyped free-form `query` object are never explained. No mention of format for the lease id, what query filters (if any) are honored, or defaults. The description only tells the agent to go look elsewhere.

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 is just the raw endpoint restated twice (identical sentence duplicated), plus an operation ID and a pointer to describe_operation. There is no verb/resource explanation of what an 'accounting-reset-preview' actually returns or means, and nothing distinguishes it from the many sibling get_accounting_leases_by_id_* endpoints. The path is the only semantic signal, making this close to tautology.

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?

No statement of when to call this versus the dozens of sibling lease-accounting GET endpoints (e.g. get_accounting_leases_by_id_journal_ent_*, get_accounting_leases_by_id_amortizatio_*). The only guidance is an implicit redirect to describe_operation, which places the burden entirely on another tool rather than telling the agent when this preview is appropriate.

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