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

Annotations already declare this a safe read (readOnlyHint=true, destructiveHint=false), so the bar is lower, yet the description adds real context: the data source (the Settings screen) and the shape of the response ('Returns each setting and the screen as rows'). It stops short of saying whether the Settings screen must already be open or what happens if it is not.

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?

One sentence, zero filler, and it front-loads what is read before listing the fields and the return shape. Every clause (source screen, field list, allowed values, return format) contributes.

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 simple single-parameter read with annotations and full schema coverage, this is close to sufficient: it documents the returned keys and their enumerated values even though no output schema exists. The only soft spot is the ambiguity about whether the Settings screen must be navigated to first.

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% with a single required 'session' parameter whose description ('Session from open_app') already explains its provenance. The description adds no additional meaning about the session parameter, which is the expected baseline when the schema fully documents it.

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?

Uses a specific verb ('Read') on a specific resource ('the phone's system settings from the Settings screen') and enumerates exactly which settings are returned, so the agent knows what comes back. It does not explicitly name the writer counterpart (set_setting), so the sibling distinction is only implied by the verb rather than stated.

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?

Usage is only implied: 'Read ... from the Settings screen' suggests this is the inspection step before set_setting, and the mention of the Settings screen hints at a navigation prerequisite. There is no explicit when-to-use/when-not-to-use guidance and no named alternative.

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