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

Annotations declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, and the description is consistent with them, adding the crucial fact that the call has no effect at all. For a deprecated stub that is the main behavioral fact an agent needs. It does not describe a return value, but a no-op has nothing meaningful to return.

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?

Two sentences, front-loaded with the decisive fact ("Retired, runs nothing") before the remediation instructions. Every clause carries actionable information: replacement tool, argument values, and how to find the task_id.

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?

Given a one-optional-parameter stub with no output schema and non-destructive annotations, the description covers everything needed to act correctly: it says the tool is dead and gives a complete, executable substitute path. No gap remains that would cause a mis-call.

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?

Schema description coverage is 100% and the single conversation_id parameter is documented exhaustively in the schema itself, so the description need not repeat it. The description does not mention conversation_id at all, which is acceptable here since the tool does nothing, but it adds no parameter meaning beyond the schema.

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 opens with an unambiguous status statement, "Retired, runs nothing," so an agent immediately knows the tool is a no-op rather than a browser control. It then names the correct sibling (well_update_task) and the exact arguments to use, which distinguishes it from every other browser tool in the sibling list.

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 explicit replacement routing: call well_update_task with the task_id and status "cancelled". It also supplies the discovery path (well_list_tasks with task_kind "browser-task" finds the task_id), so an agent that lacks a task_id knows exactly how to obtain one. Nothing about when to use this vs. alternatives is left to inference.

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