reclassify_concept

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

Annotations already signal destructiveHint=true, but the description adds substantial behavioral detail: multi-file write, permanent UID preservation, backlink redirection, starter body replacement with custom prose preservation, and default dry-run. This goes well beyond the annotations and provides safety-relevant understanding for an agent invoking a destructive operation.

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?

Two dense, front-loaded sentences with a clear warning, a concise statement of what changes, side effects, and the dry-run default. Every clause adds operational value and nothing repeats the schema or annotations.

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 destructive multi-file write with seven parameters, the description covers the transaction model, side effects, UID behavior, and body preservation, which is strong. Minor gaps remain around confirm as the commit trigger, expected_mtime concurrency, and the conditional requirement that domain is needed for capability/element, though some of that is present in the schema.

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?

The description maps meaningfully onto parameters: newKind affects the concept kind, newSlug/domain cover the optional slug/domain changes, and body is reflected in the 'preserving custom prose' behavior. With schema coverage at 57%, the description partially compensates for undocumented params, though confirm and expected_mtime are still left to inference.

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 a specific verb ('reclassify'), the resource ('concept'), and the exact scope: changing the concept kind and optionally its slug/domain. It also differentiates this from rename_concept by noting backlink redirection and from patch_concept by framing it as a multi-file write. The behavior is unambiguous and distinct from sibling tools.

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 gives actionable context by referencing rename_concept and by stating that it defaults to dry-run, which tells the agent that a preview step is expected. However, it never explicitly states when to prefer this over patch_concept, rename_concept, or delete_concept, nor does it state exclusions or prerequisites for reclassification.

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