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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real context beyond that by equating the effect to tapping the form, noting the open screen shows the result, and enumerating the two failure modes (not_installed, action_failed with reason). Missing are permission/auth or idempotency details, but the mutation and error profile is well disclosed.

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?

Three sentences, front-loaded with what the tool does, followed by effect and then failure modes. No filler, no repetition of schema or annotation content.

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?

With no output schema, the description still tells the agent where the outcome surfaces (the open screen) and how failures are reported, which covers the key gaps for a 4-parameter mutation tool. Slightly short on what the immediate return payload looks like, but nothing essential is missing.

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%, so the baseline is 3, but the description adds meaning the schema does not: session originates from open_app, action is an action name drawn from the spec, and the add_task/{ title } example shows how the free-form input object maps to a named action. That linkage is genuinely useful for a nested-object parameter.

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?

States a specific verb and resource ("Run one action of an app made with create_app, by name, with its input") and anchors it to recognizable siblings (create_app, open_app). The add_task/{ title } example makes the unit of work concrete and distinguishable from open_app or create_app.

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 spelled out: session comes from open_app and the action name comes "from the spec," and the not_installed error hints at a prerequisite. It never explicitly states the when/when-not or names an alternative for a given task, so an agent must infer the ordering itself.

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