df_write_measure

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower. The description adds valuable specific behavior beyond annotations: replace 'RESETS every optional field you do not pass' and update is a partial PATCH. This discloses the main destructive trap an agent could fall into. No contradiction with 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?

The description is compact and front-loaded: the core action and resource appear immediately, and the mode distinctions are packed into three tight sentences. The only minor redundancy is the opening 'WRITES TO DATAFORGE,' which restates what the tool name and the next sentence already convey.

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?

This is a high-complexity tool with 25 parameters, no output schema, and low schema coverage. The description explains mode behavior but leaves most fields semantically unexplained, does not mention the idempotency_key behavior beyond what the schema says, and provides no example or guidance about expected responses. An agent has enough to choose a mode but not enough to confidently fill the full payload.

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 only 40%, so the description should compensate for the many undocumented parameters. Instead, it mostly restates what the schema already says about mode (PUT resets optional fields, PATCH changes only supplied fields) and about measure_id being required for replace/update. It adds no meaning for the many optional fields like block, group, status, formula, restrictions, or original_source.

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 action and resource: 'Create, replace or update a measure in a project version.' It clearly distinguishes this single-measure write tool from siblings like df_bulk_write_measures, df_delete_measure, and df_write_fact by naming the exact resource and operation modes.

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 solid guidance for choosing among the three modes (create vs replace vs update) and notes that replace/update require measure_id. However, it does not say when to choose this tool over a sibling like df_bulk_write_measures, and it offers no exclusions or alternative-tool routing for the single-vs-bulk case.

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