workflows_run_project_log_workflow

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

With no annotations provided, the description carries full burden. It discloses the orchestration side-effect (writes to Azure AI Search vector index), the deployment-based behavior switch (Foundry API vs local Azure OpenAI), and that the combined result is stored as a single entry. This is meaningful behavioral disclosure beyond what schema captures, though it doesn't specify auth requirements or failure modes.

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 structured with numbered agent steps for readability, making the orchestration flow easy to parse. Every sentence contributes meaningful information. It could be slightly more compact but the markdown structure improves scannability and the length is justified by the workflow complexity.

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 tool has moderate complexity (two-step orchestration, deployment-based branching logic, vector-index side effect). The description covers the workflow steps, the storage outcome, and the deployment variance. With an output schema present, the description need not explain return values. It adequately captures the workflow's full scope for an agent to invoke correctly.

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 100%, so the baseline is 3. The description does describe the workflow's inputs implicitly (story_url drives CaseStudyAgent) but doesn't add format or additional semantics beyond what the schema already provides. The description's added value on parameters is minimal but not zero given the top-level workflow context.

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 uses a specific verb ('Run') with a clear resource ('project-log ingestion workflow') and even details the two sequential agent steps (CaseStudyAgent, ArchitectureAgent) plus the final vector-index storage. It clearly distinguishes itself from sibling tools like agents_invoke_agent and index_ingest_project_log by describing the orchestrated multi-step composition.

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 clearly states when to use this tool (running the full project-log workflow). While it doesn't explicitly name alternatives to avoid, it does describe the internal orchestration (agents invoked via Foundry API vs. running locally), which gives context on how it compares to lower-level siblings. It lacks explicit when-not-to-use guidance but provides decent context.

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