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

The description discloses the concrete side effects beyond what the annotations provide: it POSTs to DataManagementDefinitionGroups and DataManagementDefinitionGroupDetails with AutoGenerateMapping=Yes, revealing exactly which OData endpoints are touched and that FO auto-generates mappings. It also elaborates the idempotency annotation by explaining the practical meaning (existing project reused, entities present are skipped). No contradiction exists between the description and the annotations.

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?

All five sentences earn their place: purpose, mechanism, idempotency, workflow routing, and parameter guidance each carry distinct value. The purpose is front-loaded in the first sentence. It is on the longer side, but the tool is complex (4 parameters, domain-specific DMF concepts, several siblings) and every clause contributes, so the length is justified.

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?

The description covers the key prerequisites (existing source data format, no X++ customization) and the post-condition workflow for exports. With no output schema, a brief note on what the tool returns would strengthen it, and the import path's next step (dmf_import_file exists among siblings) is not mentioned. These are minor gaps against an otherwise dense and sufficient description for a 4-parameter tool.

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?

With 100% schema coverage, the baseline is 3, but the description adds meaningful guidance beyond the schema: it warns that sourceName must reference an EXISTING format and gives a concrete example ('comma-delimited format'). It also explains why entities is a comma-separated string by describing the underlying per-entity row creation, and it contextualizes operationType by noting EXPORT projects are later run by dmf_export_package.

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?

The description opens with a specific verb-plus-resource ('Create (or extend) a DMF data project') and immediately disambiguates the operation modes (EXPORT or IMPORT). It distinguishes itself from the sibling dmf_export_package by clarifying that this tool only builds the project while running it is a separate step. The naming convention also differentiates it clearly from dmf_apply_entity_filter and dmf_import_file.

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 description gives explicit workflow guidance: 'For EXPORT, the project can then be run with dmf_export_package,' which tells the agent this tool is a setup step and points to the correct sibling for execution. It also states the idempotent reuse behavior, which informs when calling it again is safe. However, it does not explicitly contrast with dmf_import_file or address when a user would need custom X++ mapping instead.

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