scf_get_document_history

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

With no annotations provided, the description carries the full disclosure burden. It does add real behavioral value: declaring the operation is a read requiring only the viewer role, and enumerating what data is covered (who/when/why and per-version changes). The gap is that it omits response shape, pagination/sampling behavior for long histories, and any failure modes — details that matter more here precisely because no output schema exists to fill them.

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?

A single, information-dense sentence. Purpose is front-loaded, the safety-relevant '(read — viewer role)' tag is placed parenthetically, and the trailing clause adds content coverage with zero filler. Every element earns its place.

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?

With only 2 simple parameters fully documented in the schema and a read-only operation, the description covers purpose, safety, role, and data scope adequately. The one notable omission is the return format, which matters because there is no output schema; a history tool with potentially many versions would benefit from stating whether results are paginated or fully returned.

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 100%, and both parameters carry useful descriptions ('Organization UUID — obtain from scf_list_organizations', 'Generated document UUID — obtain from scf_list_documents') that tell the agent how to source values. The tool description itself adds no parameter detail, which is acceptable at the high-coverage baseline of 3.

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?

States a specific verb-resource pair ('Get a document's version and transition history') and goes on to define the scope precisely: who moved it between lifecycle states, when, why, and what each generation changed. This clearly separates it from siblings like scf_get_document (current document), scf_transition_document (performs the move), and scf_list_documents (enumerates documents), so an agent can distinguish them without opening the schema.

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 '(read — viewer role)' parenthetical implies the tool is safe to call with minimal permissions and positions it for audit/history tracking. However, there is no explicit when-to-use-versus-alternatives guidance, no named sibling to route toward (e.g., 'use scf_get_document for the current state'), and no exclusions stated. Context is clear but the only contrasting signal is implicit in the resource named.

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