set_camt_matching

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

Goes meaningfully beyond the annotations by bounding the blast radius: it tunes ranking and the review event only and 'never touches the mandatory exact amount + currency gate', plus 'one row per workspace', which explains the idempotentHint. The destructiveHint=true is only obliquely covered by 'one row per workspace' — the description never says existing values are overwritten or that omitted fields may be reset, which is the main residual gap.

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?

Two dense sentences with the two tunables front-loaded and the safety constraint second; no filler. The parenthetical notation ('A36 §6b', '(0-60, default 5)') is compact rather than wasteful, though the density makes it slightly harder to scan.

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 4-parameter configuration tool with no output schema and no annotations covering the overwrite behavior, the critical unanswered question is whether omitted fields keep their current values or revert to defaults — an upsert ('one row per workspace') could mean either. The matching-semantics coverage is strong, but that update-semantics gap matters for correct invocation.

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% and the schema declares no enums, so the description carries the load and does so for the two behavioral knobs: valueDateWindowDays is given a 0-60 range and default 5, reviewThreshold its allowed values (any|medium|high) and default any. It adds nothing for workspaceId or idempotencyKey, which are self-evident but still undocumented.

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 ('Tune') and a precisely scoped resource ('workspace debit-matching', with a domain reference to A36 §6b), then names the two knobs it exposes. An agent can tell this apart from sibling configuration tools like set_bank_standard or set_qr_auto_apply 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?

Usage is implied by describing what the two settings affect (value-date proximity signal, review-confidence floor), which is enough to infer 'use when tuning debit match strictness'. However, no sibling alternative is named and no when-not condition is given, so routing between this and the many other matching tools (set_bank_standard, match_three_way_override, set_qr_auto_apply) is left to inference.

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