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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered, but the description adds the non-obvious fact that the tool performs no action in Dribbble whatsoever despite its name. Given there is no output schema, it also sketches the return value ('screens, buttons, fields' step by step), which is real added value. It stops short of describing output format or length, but the core behavioral surprise is 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?

The critical correction ('opens nothing by itself') is front-loaded in the first sentence, which is good. However, 'from ChatGPT, Claude or any AI agent' is filler, and the closing sentence about Dribbble's API v2 coverage is a tangentially relevant caveat that does not help an agent decide or invoke. Two of three sentences are load-bearing; the last one is padding.

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, the description covers the essentials: what it returns, that it acts on nothing, and which tools to use afterward. An agent has enough to invoke it and sequence the follow-up correctly. Minor gaps remain around the format and granularity of the returned instructions.

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, which is the baseline-4 case. The description correctly implies no inputs are required to retrieve the guide, and there is no parameter ground left uncovered. Nothing further needs to be said here.

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 makes the real behavior explicit: it 'Returns how to do it in Dribbble step by step (screens, buttons, fields) and opens nothing by itself', which is not what the name 'upload_shot' implies. That distinction is the single most important fact for an agent choosing this tool. It loses a point because the name/title still promises an upload action, so the description is doing corrective work that the identifier undermines.

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 handoff sequence: call this first to get the walkthrough, then 'do it with the cotlet_browser_* tools in the user's Dribbble Cloud Browser'. That effectively names the alternatives and the order of use. It does not contrast with the other Dribbble siblings (dribbble_list_shots, dribbble_get_pro_analytics) or with cotlet_app_guide, which could plausibly serve a similar guidance role.

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