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

Annotations already declare idempotentHint=true, destructiveHint=false, and openWorldHint=false, so 'Repeating restore is safe' and 'No external service is contacted' largely restate structured data. The description nonetheless adds real behavioral value: the original encrypted data and provenance are retained, so the agent knows this is a lossless, non-destructive reversal of a soft delete.

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?

Three short sentences, no filler, and the core effect ('restore ... to normal lists and reads') is front-loaded ahead of the safety notes. Every clause earns its place.

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 two-parameter restore with no output schema, the description covers the effect, the data-retention guarantee, idempotency, and external-service isolation. It stops short of noting what a stale expected_revision does (only in the schema) or any authorization nuance behind 'owned'.

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 50%: run_id is undocumented in the schema but is self-evident as the run identifier from the tool name, while expected_revision carries its own description in the schema. The description adds no parameter-level meaning of its own, so the baseline 3 is appropriate.

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 ('Restore one owned soft-deleted Accounting run') plus scope (single, owned, soft-deleted) and the observable effect ('to normal lists and reads'). This cleanly separates it from delete_accounting_run, get_accounting_run, and list_accounting_runs without opening any schema.

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 precondition 'soft-deleted' and 'owned' tells the agent when the tool is applicable, but no alternative is named (e.g. that delete_accounting_run creates the soft-deleted state, or that list_accounting_runs surfaces such runs). Usage is implied rather than routed.

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