start_visual_session

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

With no annotations provided, the description carries the full burden and meets it: it discloses the exact failure mode (typed TOOL_REMOVED error), the reason (v0.9.62 implicit contract), and where to find the migration path. This is behavioural disclosure well beyond what the schema conveys.

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 removal status is front-loaded in the very first token, which is the right priority. It is dense but each clause adds actionable information (error type, replacement mechanism, doc pointers); only slight redundancy between the version tags and the closing references.

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?

For a tombstoned tool with no output schema, everything an agent needs is present: the deprecation, the runtime error, the replacement contract, and the documentation anchors. Nothing about selection or invocation remains ambiguous.

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%, so the schema already documents all four parameters (task, client, detail, tab_id) in detail. The description adds no parameter-level meaning, which is the baseline-3 case when the schema does the heavy lifting.

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 states a specific, unambiguous status: the tool was removed in v0.9.0 and no longer performs a start operation. It distinguishes itself from siblings by explaining that the visual session is now implicit on every action tool rather than a separate call, so an agent knows not to look for a counterpart.

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 explicitly says what happens if called (typed TOOL_REMOVED error), what to do instead (pass the required visual_reason + client bundle on action tool calls), and where the migration recipe lives. When-to-use / when-not-to-use is fully resolved: never call this; use the implicit contract.

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