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

The annotations only give the generic safety flags (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds real behavioral context beyond them — ambiguous matches abort before any mutation, failed accessibility presses fall back to coordinate taps, field writes are read back up to three times, and secure fields return an explicitly unverified success. These are exactly the traits an agent needs to interpret partial or surprising results.

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 core action is front-loaded in sentence one and the remaining sentences are dense with non-redundant facts. Minor waste: the leading '# idb-semantic-action' heading merely repeats the tool name, and a few clauses ('expect optionally guards the current AXValue') are compressed enough to need a second read.

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 six-parameter mutating tool with no output schema, the description covers targeting, failure handling, fallback behavior, and verification semantics, which is most of what an agent needs. What is missing is what a successful return looks like (element resolved, prior value, read-back result) and what error surface accompanies an ambiguous-target abort.

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 full burden and largely does: it defines what query matches against and how case-sensitivity works, what exact toggles, that value is required only for set-value, what expect guards, and that udid is optional. Only udid's actual meaning (target device selector) is left implicit.

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 opening sentence names a specific verb pair and resource: press an accessibility-identified control, or replace and verify a field value. That distinguishes it cleanly from coordinate-based siblings like idb-ui-tap and idb-ui-input, and the AXUniqueId/AXLabel targeting makes the accessibility-element scope unambiguous.

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 implied rather than stated: the query semantics, the exact:false substring mode, and the press vs set-value split tell an agent how to call it, and 'ambiguous targets fail before mutation' warns about a failure mode. However, no sibling is named and there is no explicit 'use this instead of idb-ui-tap when the element has a stable accessibility id' style routing, which matters in a 70-tool surface with several near-overlapping UI tools.

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