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

With no annotations, the description carries the behavioral burden and does well: it discloses that the result includes a download link that expires after 15 minutes, and that only a *published* version can be exported. It does not discuss permission requirements or what happens on failure, but the key temporal constraint is surfaced.

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?

Three compact sentences, front-loaded with purpose then parameter behavior, with no filler. Every clause (expiry window, version default, mode semantics) 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?

For a 5-parameter export tool with no output schema, the description covers what is returned (an export plus a time-limited download link) and the two enum-driven behaviors. It omits any note on output format or whether the export is generated synchronously, which would be the remaining gap.

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 already 100%, so baseline would be 3, but the description adds meaning the schema doesn't: default-to-latest behavior for version, the baseline pack's version 1.0, and the project-vs-managed distinction for Claude Code (repository files vs administrator-installed files). That materially improves correct invocation.

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 ('Exports a published policy pack version') and enumerates the concrete targets (Claude Code hooks, Kong, Zuplo), which no sibling tool covers. An agent can immediately tell this apart from list_policy_packs or export_eval.

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?

It gives real selection context: the version parameter is optional with a latest-by-default rule, the baseline pack maps to 1.0, and mode is only meaningful for Claude Code. It stops short of explicitly naming alternatives (e.g. 'call list_policy_packs first to obtain pack_id'), so the routing guidance is clear but not exhaustive.

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