Control Session

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

No annotations are provided, so the description carries the full burden — and it discloses almost nothing beyond the verbs themselves. It does not say whether delete is irreversible, what happens to a running session's state or streams on stop, whether restart preserves configuration, what permissions or backend attachment are required, or what happens if the target session is already stopped or does not exist.

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?

A single sentence that front-loads the operation set and appends the scoping default in parentheses. Nothing is wasted and the parenthetical default is placed exactly where it is needed.

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?

An output schema exists, so return values need not be described, and the two-parameter surface is small. But for a destructive mutation tool with zero annotation coverage, the definition should say more about consequences (delete semantics, state loss on stop) and prerequisites than a single clause provides.

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 0%, so the description must compensate: it does so for session_id by stating the default is the current graph's session, which is genuinely useful context not present in the schema. The action parameter is self-describing via its enum, but neither parameter is explained beyond that — no id format, no note on whether session_id is honoured for 'start'.

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 names concrete verbs (start, stop, restart, delete) acting on a specific resource (a session), and the scope default ("the current graph's session") is stated. It is clear what the tool does, but it does not distinguish itself from the related siblings list_sessions or session_status, which an agent might reasonably confuse it with.

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?

Usage is only implied: the tool is clearly the mutation counterpart to the read-only session siblings, but neither the description nor anything else explicitly says when to use this versus list_sessions/session_status. The note that the default target is the current graph's session is the one piece of real targeting guidance; there are no preconditions (e.g. session must exist to stop/restart) and no exclusions.

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