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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds the important behavioral trait that a still-open run's draft pack requires api_key, and clarifies that sealed runs are readable by id. This goes beyond the annotations without contradicting 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?

Two sentences; the first lists contents compactly, the second clarifies state-dependent behavior. No redundant or filler text; every phrase adds information.

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 2-parameter tool with no output schema, the description sufficiently describes what the tool returns (pack contents) and the access conditions. No missing critical information such as error cases, but those are not necessary for a read-only export.

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?

Input schema already documents both parameters with 100% coverage. The description adds the conditional that api_key is needed for unsealed runs, which clarifies the otherwise optional parameter's role. This extra context elevates it above the baseline.

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 clearly states the tool exports a run as a governance evidence pack, listing concrete contents (signed receipt, entries, node roll-up, hash-chain/Merkle check, coversheet). This distinguishes it from sibling tools like get_run by specifying the full audit pack rather than just run details.

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 provides context about sealed vs open runs and the api_key requirement, but does not explicitly mention when to use this tool over alternative siblings (e.g., get_run). No exclusions or alternative tool references are given, so usage is only implied.

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