list_incomplete_reconstructions

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: it reads only the local audit log and makes no Manager API call, plus the resume semantics of apply. No contradiction with annotations, though it does not describe pagination or staleness of the local log.

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 resource definition, then the return fields, then the resume and no-API notes. Slightly dense with parenthetical tool names, but every clause carries usable information.

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?

An output schema exists, so return-value details are not strictly required, yet the description usefully previews the payload (invoice key, repointed transactions, remaining). Complete enough to invoke and interpret safely; only minor operational details (log freshness, volume) are absent.

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?

The tool takes zero parameters, which is the baseline-4 case. Nothing is needed beyond confirming the call is argument-free, which the empty schema already implies.

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 precise resource: reconstruction attempts that started but did not complete. It even names the producing tools (propose_*_invoice_reconstruction / apply_*_invoice_reconstruction), so an agent can distinguish this from siblings like find_broken_invoice_references 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 line about calling apply again with the same proposal_token resuming from exactly this state makes the intended use case clear (inspect resumable work before re-applying). It stops short of explicit when-not-to-use guidance or a named alternative, so it is strong context rather than a full routing rule.

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