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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with that ('does not start a build, publish, or run a server'). It adds the ownership scoping ('owned') and the artifact type, but says nothing about how the artifact is returned, whether export is synchronous, or size/time limits — meaningful unknowns for an export operation.

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 short sentences, front-loaded with the positive capability before the exclusions. Nothing is padded, though the final sentence 'Code has no server-side export' is terse to the point of ambiguity about what a `code` export actually returns.

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 required enum parameter with five values and no output schema, the description should cover all enum values and indicate the return shape. It covers three of five products and the artifact format but not delivery (URL, stream, archive location), leaving an agent unable to predict results for `code` and `cloud`.

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 description coverage is 0%, so the description carries the burden, and it does map three enum values to output formats (studio→ZIP, mobile→ZIP, data→JSON). However, the enum contains five values; 'code' is only given a cryptic negation ('no server-side export') and 'cloud' is entirely unaddressed, and `projectId` gets no semantic detail at all.

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?

Names a specific verb (export) and concrete resources (Studio source ZIP, Mobile Expo ZIP, Data project JSON), which is far more informative than the bare name 'export'. It differentiates from deploy/eas_dispatch/status by stating what it does not do. It falls short of 5 because the resource list does not match the required `product` enum — 'code' and 'cloud' are never described.

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 clear negative routing: 'Does not start an EAS build, publish a site, or run a server,' which steers an agent toward deploy/eas_dispatch for those intents. It does not name the sibling tools or state a positive precondition beyond 'owned,' so the guidance is real but not explicit about alternatives.

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