build_ontology

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

With no annotations, the description carries the full burden and discloses substantial behavior: it invokes a model, blocks until completion, performs three builds to compare stability, and returns a run_overview-equivalent summary plus open_items, answered_items, and card. It does not discuss permissions, failure modes, or side effects beyond creating a run/version.

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 front-loaded with the core action and packs relevant details into compact clauses. It is somewhat dense but every sentence contributes necessary pipeline, versioning, or return-value 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?

For a complex multi-stage build tool with no output schema, the description explains the process, blocking behavior, return summary, and previous-version semantics. It is largely complete, though it could add more about run state, failure handling, or how open_items should be acted on after return.

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 coverage is 100%, so the schema already documents all four parameters. The description still adds meaning by explaining that purpose drives the questions the ontology should answer and that previous reuses confirmations, acceptance questions, and rules from the prior run, which goes beyond the schema's field descriptions.

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 action: uploading files and building an ontology, then lists the concrete stages (model proposal, code verification, data check, three-build stability comparison). It distinguishes the return shape from run_overview, but does not clearly separate this tool from other build-related siblings such as confirm_ontology or preview_upload.

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?

It gives one explicit usage condition: supplying previous means this is a new version of that run and inherits its confirmations, acceptance questions, and rules. However, it does not say when to use this tool versus alternatives like preview_upload or run_overview, nor does it provide exclusions or prerequisites.

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