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

Goes beyond the annotations by disclosing that the return value is a step-by-step walkthrough of screens, buttons and fields rather than data, and that it performs no action itself. This matches readOnlyHint=true and openWorldHint=false and adds genuinely useful context. It stops short of describing the shape of the guide or whether results are cached.

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 workflow (returns instructions, then drive the browser) is front-loaded in the first two clauses, but 'from ChatGPT, Claude or any AI agent' is pure filler and the closing 'Timely's official API: Timely publishes no API docs' is awkwardly phrased and adds little beyond saying there is no API.

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 zero-parameter, read-only guide tool with no output schema and full annotation coverage, the description covers what it returns and what to do next. The remaining gap is not defining the 'due back' criterion the guide will look for.

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 tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline applies; no compensating detail is required.

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 ('Find clients due back') scoped to the user's own Timely account, which distinguishes it from the browser-action siblings. What 'due back' actually means operationally (returning appointments? follow-ups?) is never defined, so the resource is clear but the criterion is fuzzy.

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?

Explicitly says it 'opens nothing by itself' and that the agent must then execute the steps with the cotlet_browser_* tools, which is real routing guidance versus the browser primitives. It does not name timely_list_clients as the alternative for listing clients, leaving that comparison to inference.

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