alter_voucher

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

With no annotations, the description carries the behavioral load and does so substantively: it discloses the field-level merge model, that ledger_entries/inventory_entries/stock_in/out REPLACE rather than append, that totals must still balance, and that existing single bill references are preserved automatically. These are non-obvious destructive semantics an agent must know. It omits return behavior and whether a backup is taken (only implied via the dry_run schema field).

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?

Front-loaded with the verb and the identification key, then proceeds to the highest-risk semantics (replace behavior). Dense but each sentence carries information; not padded.

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 8-parameter, deeply nested mutation tool with no annotations and no output schema, the description covers the critical mutation semantics that the schema cannot convey. The remaining gap is return-value/backup behavior, which is moderate but not disqualifying given the schema's dry_run hint covers side-effects.

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 only 50%, but the description compensates on the highest-risk parameters: it clarifies the replace semantics of ledger_entries, inventory_entries, and stock lines, and the auto-retention of bill_allocations. It adds meaning genuinely beyond the schema for the `changes` object, though it says nothing about company, voucher_type, or the date/guid top-level params.

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+resource ('Modify an existing voucher') and names the identification key. It doesn't explicitly contrast with create_voucher/delete_voucher, but the mutate-existing framing distinguishes it well enough that an agent won't confuse it with creation or deletion.

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?

Gives a preference signal ('master_id (preferred)') which is a partial usage cue, and explains that only fields in `changes` are touched. But there is no when-to-use vs alternatives guidance beyond that, and the other identification routes (guid, voucher_number+voucher_type) are not framed as fallbacks.

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