alert

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

With no annotations, the description carries the full burden and does so: it discloses the 90s timeout, the ALERT_BUTTON_NOT_FOUND outcome that taps nothing, the platform-specific label-matching rules (English preference ordering, simulator localized strings vs. Limrun English-only), refusal on equal-ranked or unknown labels, and the warning never to assume a timeout means nothing happened. That is unusually rich disclosure of side effects and failure modes for a mutation tool.

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?

Well front-loaded — purpose first, then usage rule, then platform nuance — but the middle is a dense run-on of nested clauses ('on iOS simulators, local XCTest also recognizes...') that is hard to scan. Every sentence carries information, so it is not padding, but it is not economically structured either.

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 mutation tool with no annotations and 18 parameters, it covers side effects, failure modes, and platform divergence thoroughly. The notable gap is the return shape: with no output schema, the description never says what 'get' yields (label list? visibility flag? structure of ALERT_BUTTON_NOT_FOUND), leaving the agent to discover the response format at call time.

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 89%, so the schema already documents nearly all 18 parameters. The description adds behavior for the action values (accept vs. dismiss semantics differ radically per platform) and mentions the 90s timeout against timeoutMs, but says nothing about the device-resolution parameters (udid, device, serial, platform, target) or responseLevel/mcpOutputFormat. Baseline 3 is appropriate.

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?

Opens with a specific verb set over a specific resource: 'Inspect, wait for, accept, or dismiss a platform alert,' which maps directly onto the four action enum values. An agent can distinguish this from siblings like get, wait, or press without inspecting the schema.

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 real usage rules: 'Use get before acting when the alert content matters' and 'Inspect again after an unconfirmed action.' It also implicitly distinguishes wait (observe) from accept/dismiss (mutate). It stops short of naming sibling alternatives (e.g., when to use snapshot or find instead) or stating prerequisites such as needing an active session or lease.

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