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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'opens nothing by itself', resolving what would otherwise look like a write tool. It also discloses the target environment (the user's own account, their Cloud Browser session) and the follow-on tools needed to actually commit the change. It stops short of stating auth/prerequisite requirements (logged-in Cloud Browser session) or whether the call consumes credits, which matters given the cotlet_balance sibling.

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 constraint ('returns how to do it... opens nothing by itself') is stated early, which is good, but the opening clause 'from ChatGPT, Claude or any AI agent' is filler. The closing paragraph about DonorPerfect's XML API and the dated 'no official MCP server (checked 23 Oct 2026)' is background justification rather than call-relevant instruction and dilutes the message.

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, no-output-schema tool the description covers the important ground: what it returns (screens, buttons, fields), that it has no side effects, and which tools to use next. What is missing is the handoff contract – what gift data the agent must gather and carry into the browser step, and any preconditions on the Cloud Browser session.

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, so the baseline is 4, but the description creates a real ambiguity: 'add gift' normally needs donor, amount, date and fund, yet no inputs are declared and the text never explains that gift details are conveyed conversationally and the returned steps are generic. The agent has to infer how its data reaches DonorPerfect. The API note likewise adds no parameter meaning.

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 names a specific verb and resource (add a gift in the user's own DonorPerfect account) and, crucially, clarifies that the tool returns step-by-step instructions rather than performing the write. That reframing is the useful part, but the name/title ('Add gift') pulls the opposite way, so an agent only learns the real behavior by reading the whole first sentence. It also never names the closest siblings (donorperfect_add_contact, donorperfect_create_pledge) to say why this one is different.

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 an explicit two-step workflow: call this to get the screens/buttons/fields, then execute with the cotlet_browser_* tools in the user's DonorPerfect Cloud Browser. That is clear when-to-use and how-to-continue guidance. There are no exclusions (e.g. when to prefer a native API-based gift tool over the browser path), which keeps it from a 5.

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