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

Annotations already declare the write/idempotent/non-destructive profile, so the bar is lower, and the description still adds meaningful behaviour: definition-only by default, full data only when explicitly requested, and asynchronous queue-and-poll execution. It stops short of saying where the package lands or how long the job persists.

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, no filler, and the primary behaviour and the default are front-loaded before the async follow-up. Every clause carries information the agent needs.

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, the description correctly redirects the agent to get_job for results and discloses the asynchronous job model, which is the key missing piece an agent would otherwise guess at. Minor gaps remain around the fate of the temporary workspace and package retention, but nothing essential to a correct call is absent.

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 only 50% (projectId and dataPolicy are undescribed), so the description has to compensate. It does so for the ambiguous parameter: the phrase 'definition-only package by default or an explicit full-data package' gives concrete meaning to the omitted/included dataPolicy enum and its default, which the schema alone leaves opaque.

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 (export a project package) plus the two output variants it supports, which immediately separates it from import_project and the analyser/renderer siblings. It does not, however, name an alternative sibling (e.g. get_download_link) by name, so an agent gets the purpose but not the routing.

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 an explicit follow-up instruction: the call queues a hosted job, and get_job is named as the way to retrieve the result. That is real when-to-use guidance for the async pattern, but there is no guidance on when to prefer full-data export, or how this differs from import_project / get_download_link.

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