sessions

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful scope detail beyond that — that it returns all open sessions including other agents' workspaces and flags yours — but says nothing about ordering, volume, or whether closed sessions are excluded.

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 short sentences with no filler, and the scope statement is front-loaded before the sibling reference. The terseness borders on cryptic terminology rather than wasted words.

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 output schema, the description should convey what comes back; it mentions ids and traces but not their structure or shape, so an agent knows roughly what to expect but not how to read the result.

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 and the description correctly offers no parameter guidance, which is the appropriate baseline. No misleading parameter claims are made.

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 identifies the resource as "the open sessions" but the clarifying gloss ("the user's wtf windows and agents' workspaces") is internal jargon an outside agent cannot decode with confidence, so it is unclear what a session actually is. It does at least signal the returned fields (ids, traces) and marks which entries are the caller's own.

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 routes explicitly to the sibling tool: "`open` starts one or switches between yours" implies this tool is for inspection rather than creation or switching. There is no explicit when-not guidance, but the alternative and its condition are named.

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