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

With zero annotations the description carries the full burden and does substantial work: pricing and payment rail (x402, eip155:8453, EOA EIP-712 only, ERC-1271/6492 unsupported), transport limit (64 KiB MCP body), and an explicit trust caveat (input facts unauthenticated). It does not state whether the tool is read-only/non-mutating in a machine-checkable sense or describe the shape of the result, leaving a real gap for a tool with no annotation coverage.

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 core purpose leads the block, followed by constraints and disclaimers in descending priority; every clause carries information. It is dense and bracket-loaded, but nothing is redundant or 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 a one-parameter tool with no annotations and no output schema, the description covers payment, batch size, payload limits, trust assumptions and matching criteria. The notable omission is what the response contains — whether duplicate groups, conflicting amounts and per-record diagnostics are returned — which the agent must infer.

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: it names the matching keys (supplier, reference/document identity, amount, currency) that correspond to the required item fields, and 'exact decimal strings' signals amount comparison is lexical, not float-normalized — meaning beyond the schema's regex. It still never mentions record_id, document_type (invoice vs credit_note) or the required-field contract, so some semantics rely on the schema alone.

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 (compare invoice records) plus the exact semantics being checked: repeated supplier/reference/document identity and conflicting amounts or currency. Scope (up to 1000, caller-supplied) is stated, and no sibling tool overlaps with invoice duplicate detection, so the agent can route unambiguously.

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?

Explicit negative scope — no external calls, no accounting certification, no payment decision — tells the agent when this tool is NOT the right answer, and 'caller-supplied' plus 'input facts are not authenticated' warns against treating it as verification. It stops short of naming a positive trigger scenario or an alternative, but with no close siblings that gap is minor.

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