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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description clearly states that the tool downloads and installs a build, and that it adds the build to the user's app library—a side effect beyond the primary action. However, it does not mention other potential behaviors such as whether it checks for device connectivity, handles authentication, or has any rate limits. Given the lack of annotations, this is a strong disclosure of the most critical side effect.

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?

The description is three sentences long and wastes no words. It front-loads the core action, then adds the important side effect (library addition and future installation path), and concludes with guidance on obtaining the releaseId. Every sentence provides unique value.

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?

Given there are 4 required parameters, no output schema, and no annotations, the description does well to explain the tool's purpose, side effect, and parameter sourcing. It does not explain what happens if the device is not connected, what output the tool returns (e.g., success/failure), or how to handle errors. However, for a tool that combines two well-understood actions (download + install), the description is fairly complete. A mention of return behavior or error cases would push it to a 5.

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 100%, with each parameter having a description that indicates its source (e.g., 'Device UDID to install on', 'Firebase app id, from firebase_list_apps'). The description adds context by explaining the tool's two-step workflow and referencing sibling tools for parameter values, but does not add additional parameter-level semantics beyond the schema. With full schema coverage, the description still earns a slightly above-baseline score because it helps the agent understand where to obtain the parameter values.

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 very specific action: downloading a build from Firebase and installing it on a connected device in one step. It clearly distinguishes the tool from its sibling `app_install` by noting that the build is also added to the user's app library, so subsequent installs only need `app_install`. It also references `firebase_list_releases` for obtaining a `releaseId`, making it easy for an agent to understand how to chain tools.

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 explicitly tells when to use this tool versus alternatives. It states that after the first installation, subsequent installations on other devices should use `app_install` instead. It also instructs the agent to use `firebase_list_releases` to pick a releaseId, noting that 'the latest build' is the first entry returned. This provides clear context on prerequisites and when to use sibling tools.

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