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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, and the description corroborates them ('opens nothing by itself') while adding genuinely new context: what the response contains (step-by-step screens/buttons/fields) and why browser automation is required (no public API or developer docs). It does not disclose that with zero inputs the guidance must be generic rather than tailored to a specific client or group, nor whether an authenticated Cloud Browser session is a prerequisite.

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 the action and the crucial 'returns instructions, not execution' caveat before the handoff instruction. The final sentence is slightly awkward and repeats the product name ('PT Distinction's official API: PT Distinction publishes no public API or developer docs'), but it earns its place by justifying the browser-automation route.

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 carries the burden of describing returns and does so adequately (screens, buttons, fields). For a read-only guide tool with no parameters and full annotation coverage, the remaining gaps — whether guidance is generic, and whether a live Cloud Browser session/auth is needed first — are modest rather than disqualifying.

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?

The schema has zero parameters and 100% coverage, so there is nothing for the description to disambiguate — the baseline of 4 applies. The one thing it could have clarified is the consequence of parameterlessness: the returned steps are account-agnostic and the agent must gather client/group identifiers itself.

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 description states a specific verb+resource ('Add client to group') and immediately reframes the tool's real output: step-by-step instructions covering screens, buttons and fields rather than an executed change. That reframing makes the tool's nature unambiguous, though it does slightly fight the imperative name and never explicitly contrasts this guide tool with pt_distinction_add_client or pt_distinction_assign_program.

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?

It gives a clear usage contract: this tool 'opens nothing by itself' and is followed by 'do it with the cotlet_browser_* tools in the user's PT Distinction Cloud Browser' — a named alternative family plus the handoff condition. It stops short of saying when NOT to use it or how it relates to cotlet_app_guide, which likely overlaps as a guide source.

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