inspect_app

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 explicitly: it is read-only and enumerates what it will NOT do (no app launch, focus, permission request, page content, browser attachment). It also discloses the return shape, compensating for the absent output schema.

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?

Front-loaded with purpose in the first clause, then returns, then constraints, then usage in a single tight block. Dense semicolon-packed clauses are efficient, though slightly heavy for the amount of information conveyed.

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?

Two optional parameters, no annotations, and no output schema, yet the description supplies the missing pieces: what it returns, what it abstains from, and how it relates to ax_read. An agent has everything needed to call it correctly.

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%, so both parameters are already documented; the description largely restates the omission semantics and the details=true diagnostics rather than adding syntax or format detail. Baseline 3 applies when the schema does the heavy lifting.

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?

Specific verb ('Inspect') plus resource ('a running macOS application's interaction options') and an explicit second mode (discover Chromium apps when app is omitted). It names ax_read as the tool for ordinary native interaction, so an agent can separate it from the ax_* and chrome_* siblings without reading any 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?

States when to use it ('optionally for setup/discovery') and where the default path lies ('ordinary native interaction still starts with ax_read'), which routes the agent to the correct alternative. Nothing is left to inference about positioning.

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