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

Given readOnlyHint=true and destructiveHint=false, the description adds real context beyond annotations: it states the return shape (screens, buttons, fields), that nothing is opened, and that Bloom has no public API, only a Zapier app. The Zapier provenance and the 'checked Nov 2026' date are useful for the agent to know why browser automation is required.

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 message lands early, but the opening clause ('from ChatGPT, Claude or any AI agent') is filler, and the closing API/Zapier sentence is bulky for its informational value. The two-step instruction is split awkwardly by a semicolon-and-'then' construction that takes a second read.

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 parameters, no output schema, and read-only annotations, the definition covers what an agent needs: what is returned, that no side effect occurs, and which tools to chain next. Missing only an explicit statement of what the guide covers if the target payment details are unknown or unsupported by Bloom's UI.

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; the baseline for a no-parameter schema applies. The description's silence on inputs is appropriate rather than a gap.

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 resource (Bloom payment recording) and immediately clarifies that the tool returns a step-by-step guide rather than performing the action: 'Returns how to do it in Bloom step by step (screens, buttons, fields) and opens nothing by itself'. This resolves the tension with the 'record payment' name, though the name itself remains misleading until the agent reads the text.

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 routes the agent clearly: get the guide here, then execute with the named cotlet_browser_* siblings in the Bloom Cloud Browser. It does not compare against the other bloom_* siblings (create_lead, send_invoice) to say when this one is the wrong choice, so the guidance is clear but not exhaustive.

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