export_ttl

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

With no annotations provided, the description carries the full burden and does so: it discloses that files are written to a local folder, that same-named files are overwritten, that a manifest .ontopoc-export.json is left behind, that files listed in the prior manifest but absent this run are deleted (returned in `removed`) while files outside the manifest are untouched, and that a non-bare filename aborts the entire export with zero files written. It also describes the return payload shape and explicitly notes file contents are not returned.

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?

Front-loaded with what gets exported, then the naming/manifest semantics, then the error condition — a logical order with no filler. It is dense (a long single block rather than separated points), which slightly hurts scanability, but every sentence supplies non-redundant 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?

Despite having no output schema and no annotations, the description defines the return structure ({dir, files:[{name, path, bytes}], total_bytes, removed}), side effects (manifest file, overwrite, deletion of stale files), and failure behavior. For a write-side-effect export tool with two parameters, that is complete enough 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 coverage is 100% and both parameters (out_dir, saved_as) are already documented in the schema, so the baseline is 3. The description adds the default out_dir path pattern and confirms saved_as comes from list_runs/build_ontology, plus the failure mode for invalid filenames — useful but marginal beyond the schema.

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 names the operation (export Turtle per W3C standard) and enumerates the exact artifacts produced: ontology.ttl (OWL classes, fields, relations, identification keys), data.ttl (objects named by identification value), and shapes.ttl (adopted rules as SHACL). It also states a scope boundary — objects and relations judged invalid are excluded — and the sibling names export_forms/export_mermaid/export_pipeline_spec make the format-specific distinction clear.

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?

Usage is implied by the artifact list: an agent can infer this is the tool for Turtle/RDF output rather than forms or mermaid. However, the description never explicitly states when to choose this over the sibling exporters, nor does it state prerequisites (e.g., that an ontology must already be built/confirmed before export). It documents re-export behavior but not selection guidance.

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