set_taxing_scheme

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

With no annotations, the description carries the full behavioral burden, and it does add real value by revealing the tool is preview-only until the adapter/canary are ready and that it replaces a deprecated immediate write. However, it omits key traits for a 10-parameter write tool: idempotency behavior, what the hashes and previewToken gate, and what happens once apply is enabled.

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 short sentences with no wasted words and the deprecation context front-loaded. The tradeoff is that the terseness tips into crypticness rather than efficient completeness.

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 10-parameter tool with nested objects, an enum, conditional preview/apply flow, and no output schema or annotations, this description is far too thin. It neither explains the parameter contract nor the preview-to-apply lifecycle, leaving the agent without enough to invoke it 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 0% across 10 parameters (mode, dryRun, values, previewToken, idempotencyKey, taxingSchemeId, three hash fields, expectedEntityTimestamp), and the description explains none of them. Critical precondition-style params like expectedDesiredHash and previewToken are left entirely undocumented.

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 identifies the resource (taxing-scheme write) and frames itself as a preview-first replacement, but the actual verb is muddled: it says 'Apply remains unavailable,' so it is unclear whether the tool currently performs any write at all. It also fails to distinguish itself from the sibling upsert_taxing_scheme, leaving the agent guessing which to call.

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 discloses one constraint (apply is not yet available, so only previewing works) but gives no when-to-use guidance or routing versus upsert_taxing_scheme / list_taxing_schemes. The agent must infer the correct alternative entirely on its own.

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