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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them ('opens nothing by itself'). Beyond the annotations it adds genuinely useful behavior: the return is a step-by-step procedure listing screens, buttons and fields, rather than a performed action or raw data. It stops short of describing format, length or how the steps are scoped to a specific submission.

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 behavior and the 'opens nothing by itself' caveat are front-loaded in the first two sentences, which is the right ordering. It is slightly padded by enumerating 'ChatGPT, Claude or any AI agent' and by the trailing API-v2 note, which reads as an aside rather than guidance.

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 return-value burden and does so — an ordered procedure of screens, buttons and fields — plus the handoff to the browser tools that actually apply the change. It omits only how the guide is targeted at a particular submission, given that no input identifies one.

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 (schema coverage 100%, empty properties object), so there is no parameter semantics for the description to compensate for. Per the baseline for zero-param tools, a 4 is appropriate; the description correctly implies no per-submission identifiers are needed as input.

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 says specifically that the tool returns a step-by-step guide for editing a submission in the user's own 123FormBuilder account, and explicitly clarifies 'opens nothing by itself' — resolving the ambiguity in a name that sounds like a mutation. It distinguishes itself from the cotlet_browser_* siblings by naming them as the tools that actually perform the edit. Minor deduction because the name ('edit_submission') and the actual behavior (return instructions) require a sentence to reconcile.

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 clear usage context: call this to get the steps, then execute them with cotlet_browser_* in the user's 123FormBuilder Cloud Browser. However, it never states when NOT to use it — e.g., when the official REST API v2 with token login would be preferable, even though it raises that API in the same paragraph.

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