run_conversion

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing: not that this is a mutating, likely long-running job that writes artifacts into run_dir, not what permissions or runtime state are required, and not what happens on partial failure. The only behavioral hint is that this is the canonical (single) implementation path.

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?

One short sentence is technically waste-free, but for a 16-parameter pipeline entry point this is under-specification rather than conciseness. Nothing useful is front-loaded because there is essentially nothing to front-load.

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?

An output schema exists, so return values need not be explained, but that is the only gap covered. With 16 undocumented parameters, no annotations, and heavy downstream effects, the description is far too thin for the agent to invoke this correctly or safely.

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?

Sixteen parameters with 0% schema description coverage, and the description names none of them. Critical choices like llm, matching, osm_data, svg_mode, geometry_repairs, and match_profile are entirely undocumented, leaving the agent to guess values such as "legacy" or "candidate".

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?

"Run the canonical pipeline" is a near-restatement of the name with no indication of what is converted (CAD/SVG/OSM?) or what the pipeline produces. With ~60 sibling tools including auto_onboard_and_convert and export_source, the agent gets no way to tell which one actually performs a conversion run.

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?

There is no statement of when to use this versus siblings such as auto_onboard_and_convert, prepare_cad_bundle_workspace, or compile_semantic_revision. The clause "no conversion logic is duplicated here" is a design note, not a selection rule, and does not tell the agent what prerequisites must already exist.

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