df_write_fact

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

Annotations already carry destructiveHint=true and readOnlyHint=false, so the description correctly confirms a write. It adds real value beyond the annotations by disclosing the key gotcha—replace mode RESETS every optional field omitted—and the fact_id requirement for replace/update. This mode-specific destructive behavior is precisely the kind of context an agent needs. 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?

Three tightly-written sentences; the mode logic is front-loaded and each sentence earns its place. The only cost is the opening 'WRITES TO DATAFORGE' shout, which duplicates the tool name and serves mostly as emphasis. Otherwise it is efficient and well ordered.

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 23-parameter, no-output-schema mutating tool, the description adequately covers the procedural mode logic but leaves the individual fact fields unexplained and says nothing about the return/response format. Given low schema coverage and the absence of an output schema, it should describe more of the domain-specific fields and response behavior.

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 35%, so the description carries a heavy burden. It does explain the two highest-stakes parameters—mode semantics and fact_id's requirement—well. But roughly 14 parameters (block, group, status, formula, relevance, original_object, original_source, etc.) have no description in either the schema or the tool description, so the description only partially compensates for the coverage gap.

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 states a specific verb (write) and resource (a fact in a project version), then spells out the three modes: create, replace (PUT), and update (PATCH). This fully disambiguates the operation from siblings like df_write_measure and df_write_dimension, and the single-entity nature is clear against df_bulk_write_facts.

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?

Excellent internal routing: the description clarifies exactly when to use each mode—create for new facts, replace to overwrite with reset semantics, update to change only passed fields—plus a hard prerequisite (replace/update require fact_id). It does not, however, mention exclusions such as using df_bulk_write_facts for multiple facts or df_delete_fact for removal, so it stops short of addressing alternatives.

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