get_fact_history

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

Annotations already establish that this is a safe read-only operation, but the description adds useful behavioral context: pagination via next_cursor, stable event_id semantics, and the meaning of active=false for historical evidence. It also warns that source text remains untrusted data. It stops short of covering ordering, permissions, or edge cases such as missing facts.

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?

The description is compact and front-loads the core purpose before pagination and trust details. Each sentence carries relevant information, though the jargon 'exact revision proofs' reduces immediate clarity. It is appropriately sized for a read-only history tool.

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 no output schema and 0% schema description coverage, the description should carry more of the return and parameter burden. It does explain key output-like concepts such as event_id, next_cursor, and active, but it leaves input parameters undocumented and does not route the agent away from nearby siblings. It is only partially complete for the tool's complexity.

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%, so the description must compensate, but it never explains fact_id, limit, or before. It mentions next_cursor, which is not an input parameter and may confuse the agent about how to pass the before cursor. It adds some pagination meaning but does not map it to the actual parameter.

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 states a specific verb and resource: reading paginated exact revision proofs for a fact history, scoped to since feature enable. It also excludes inferred past timelines, which clarifies purpose. It does not distinguish this tool from the sibling get_facts or get_evidence_bundle, so it falls short of a 5.

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 name and by the phrase 'no inferred past timeline,' which acts as a scope exclusion. However, there is no explicit guidance on when to use this tool rather than get_facts, get_record, or search_memory, and no alternatives are named.

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