ListLeftoverSessions

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

With no annotations present, the description carries the full burden and does so: it declares read-only, identifies the data source ('Read from the session records alone, on this machine'), defines scope, and explains the lock/role semantics (built vs debugger, user absent for token logins). It even documents the non-obvious startup interaction where a new server process is born on a single leftover instance session.

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 scope are front-loaded in the first sentence, with the read-only and session tags leading. It is dense but mostly earns its length; the closing note about server-process birth behavior is legitimate context but reads as an aside that could be trimmed or moved.

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 zero-parameter read tool with no annotations and no output schema, the description supplies scope, data provenance, return fields, and an explicit next step. Minor ambiguity remains about how many destinations are covered per call and whether the list can be empty, but nothing essential to correct invocation is missing.

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 no parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The mention of 'handle' in the response fields plus 'Log one off by its handle' usefully explains what the agent does with the output, which is the only parameter-adjacent context available.

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?

Names a specific verb and resource (list leftover SAP sessions of this server's destination) and immediately bounds the population: sessions an ended, killed server process left open. It also enumerates the returned fields (handle, role, destination, user, last recorded), so the agent knows exactly what it is asking for.

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 states the selection constraint ('Only sessions of ended processes are listed') and routes remediation explicitly ('Log one off by its handle'), which clearly points at the LogoffLeftoverSession sibling without naming it. It also says 'Runs outside batch mode', a real when-not condition. The only gap is that the alternative tool is described rather than named.

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