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

The description carries real behavioral weight beyond the annotations: it discloses that the tool returns procedural instructions rather than performing actions, and explicitly states no external side effects occur ('opens nothing by itself,' 'from ChatGPT, Claude or any AI agent'). This reconciles the 'send_message' name with readOnlyHint=true rather than contradicting it. The trailing note about Podium's REST API/OAuth status adds background but not agent-actionable behavior.

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 purpose and the follow-on tool guidance are front-loaded in the first two sentences, which is well structured. The final sentence about the official REST API v4 and the 'checked 23 Oct 2026' date is tangential to invocation and slightly inflates the text, keeping it below a 5.

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 annotations already covering the safety profile, the description supplies exactly the missing piece: what the call returns (ordered screens/buttons/fields) and what to do with it. An agent can invoke and chain it without further information. Minor gap: no mention of how the actual message content is provided to the browser step.

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 and the description does not invent any, so nothing is misrepresented. However, it never explains how the target message/recipient context reaches the tool (presumably the agent supplies it inside the browser step), which leaves a small conceptual gap. Baseline for a parameterless tool is 4.

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 gives a specific verb and resource (send a message in the user's own Podium account) and immediately clarifies the actual output: a step-by-step guide of screens, buttons and fields. Crucially it disambiguates the misleading 'send' name by stating it 'opens nothing by itself,' so an agent knows this is a guide generator, not an executor. It stops short of contrasting with the similarly named podium_send_review_invite sibling, so not a 5.

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 usage sequence: call this first to get the steps, then perform them with the cotlet_browser_* tools in the user's Podium Cloud Browser. That is a clear handoff instruction naming the follow-on tool family. It does not state when to prefer this over the other podium_* mutation-style siblings (e.g. review invites, payments), leaving some routing ambiguity.

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