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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description still adds meaningful context: the call performs no browser action itself, returns procedural guidance rather than data, and explains why direct API access is not an option (Fillout's REST API cannot create or edit forms and no MCP server is documented). That is real value beyond the annotation block.

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 load-bearing caveat — that this returns instructions and opens nothing — is buried mid-sentence after audience filler ('from ChatGPT, Claude or any AI agent'). The closing API paragraph is a long tangent that does not change how the tool is invoked, and the 'checked 17 Oct 2026' timestamp is noise.

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 and no output schema, the description carries the burden of saying what comes back, and it does: step-by-step screens/buttons/fields plus a handoff to the browser tools. What it leaves out (behavior when the user is not signed in, or how much detail the steps include) is minor for a guidance-only tool.

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?

Zero parameters, so there is nothing for the description to disambiguate. Baseline of 4 applies; the schema is fully covered and needs no narrative support.

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 name and opening sentence say 'Read submissions', but the tool does not read anything — the second sentence concedes it 'returns how to do it in Fillout step by step ... and opens nothing by itself'. The actual output (screens, buttons, fields) is specific, but an agent skimming the first clause could expect submission data back. The purpose is recoverable but the framing is at odds with the behavior.

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 does route the agent onward: 'then do it with the cotlet_browser_* tools in the user's Fillout Cloud Browser', which is actionable sequencing. However, it never says when to pick this over the similar guide-style sibling cotlet_app_guide, and no exclusion or precondition (login state, form already open) is stated.

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