export_audit_log

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

With no annotations, the description carries the full burden and largely fails. It never says whether output_path writes a file or where, what happens on large reflogs (limit defaults to 100000), what permissions are needed, or whether this is read-only. The 'Requires Kiln Enterprise' line is ambiguous about whether the tool itself is gated or only the SSO/RBAC add-on.

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?

Only the first of four lines describes the tool; the remaining three are marketing boilerplate ('Enterprise adds SSO, RBAC...', 'Upgrade: https://...'). Roughly three quarters of the text does not earn its place in a tool definition.

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?

Seven parameters, zero annotations, no output schema, and an unexplained artifact_type/limit interplay leave an agent without enough information to call this correctly or safely. The one useful fact (two output formats) is the only real addition to the structured data.

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 coverage is 29%, so five parameters (start_time, end_time, branch_id, artifact_type, output_path) are undocumented in both schema and description. The description only indirectly hints at output_format by naming 'JSONL or CSV', leaving the time-range filter semantics, branch scoping, and path behavior entirely unexplained.

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 first sentence gives a concrete verb and resource ('Dump the local reflog to JSONL or CSV'), but it collides with the tool name, which promises an 'audit log' rather than a reflog. No sibling is differentiated, even though export_audit_trail and show_reflog sit in the same family, so the agent must guess which one 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?

There is no statement of when to use this versus show_reflog, get_reflog_entry, or export_audit_trail. The follow-on sentences ('Enterprise adds...', 'Requires Kiln Enterprise') read as an upsell and actually create ambiguity about whether the tool is callable at all in the current tier.

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