asset_dispose

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

Annotations only declare idempotentHint and destructiveHint=false; the description goes far beyond, disclosing atomicity, the exact append-only records written, which fields are zeroed versus preserved for historical reporting, the gain/loss sign rule, the scrap special case, tenant isolation (§H-TENANT), period locks, and a full enumerated refusal set. Idempotency semantics on idempotencyKey are spelled out concretely (replay returns the original payload, posts no second journal).

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 single dense paragraph is front-loaded with the action and structured with (a)/(b)/(c), which helps, but it also embeds GL debit/credit mechanics that are implementation detail rather than agent-actionable, and the closing CONSEQUENCE paragraph restates the opening ('takes it out of the register' / 'reverse the disposal'). Length is partly justified by 0% schema coverage, but trimming the accounting internals and the duplicate summary would lose nothing.

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?

With no output schema, the description supplies the return shape ({asset, transaction, journalEntry, gainLossRappen}), the full error taxonomy, the post-condition state of the asset, and the reversal-based correction model. An agent has everything needed to call it correctly and to interpret a refusal.

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% with 10 parameters, so the description must carry the load — and it does for the consequential ones: proceedsRappen (0 means scrap, no proceeds line), proceedsAccountId (not required for scrap), gainLossAccountId (sign driven by proceeds minus NBV), disposalDate (period-lock interaction), idempotencyKey (replay behavior), and assetId (foreign asset yields not_found). The peripheral fields notes, reason, counterpartyName, and workspaceId are never explained, keeping it below a 5.

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?

Opens with a specific verb+resource ('Dispose an active or fully_depreciated fixed asset (H06)') and immediately qualifies it as the terminal financial event, enumerating the covered transaction types (sale, scrap, donation, write-off, retirement). This is unmistakably distinct from siblings such as asset_transfer, asset_archive, or asset_update, which the description explicitly says will refuse the asset afterwards.

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?

States the preconditions and exclusions clearly: only active/fully_depreciated assets, drafts rejected with asset_not_acquired, archived assets rejected, second dispose refused with asset_already_disposed, and hard-locked periods refused. It also prescribes the correction path (reverse the journal plus compensating transaction, never un-dispose). It stops short of routing the agent to asset_disposal_preview for a dry run, which would have made it a 5.

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