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

Adds real context beyond the annotations: the operation is asynchronous, it 'changes no project data' (reconciling the readOnlyHint=false with a non-destructive outcome), and the result is an export id that must be polled. Minor gaps remain around job expiry or concurrent export limits, but the lifecycle is well disclosed.

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?

Four tight sentences, front-loaded with the action, then the mutation profile, then the follow-up procedure, then the endpoint. No sentence is redundant and nothing is buried.

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 an async job-creating tool with no output schema, the description supplies what an agent actually needs: the return value (export id), the polling target, and the success condition. The remaining parameter detail is fully covered by the schema.

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 100%, so the schema documents branch, languages, file_paths, project_url, workspace_url, and export_format on its own. The description adds one meaningful default ('Without filters it exports every file and language') but nothing about the filter interaction or format override.

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 and resource ('Start an asynchronous export of a project's resource files as a ZIP') and immediately clarifies the mechanism ('creates an export job'). It explicitly separates itself from the sibling get_export, which is the natural point of confusion.

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?

Gives the follow-up procedure explicitly ('poll get_export until its status is SUCCESS') and explains the default behavior when no filters are supplied. It stops short of contrasting with siblings like download_resource or list_resources, so the 'when not to use this' side is left implicit.

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