session_stop

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false, so the safety profile is covered. The description goes beyond them usefully by disclosing that stopping cancels the underlying operation and is irreversible without re-issuing from the originating job/restore.

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?

Front-loads the [WRITE] tag and the core action, then layers reversibility and arg notes with no filler sentences. The Args block largely restates what the schema titles already convey, which is mild redundancy.

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 3-param mutation with annotations and no output schema, the description covers action, destructiveness, reversibility, and the dry-run escape hatch. Return value shape and any auth/target-selection requirements are the only notable omissions.

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 carries the full burden and does document all three parameters. session_id points to session_list as the source, dry_run explains the preview behavior, and target is identified as a name from config — terse but adequate compensation.

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?

States a specific verb+resource ('Stop a running session') and clarifies the effect ('cancels the underlying operation'), plus tags it as [WRITE]. It does not explicitly contrast with the sibling job_stop, so an agent must infer the session-vs-job boundary itself.

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?

Adds real consequence guidance ('No undo token — a stopped session must be re-issued via the originating job/restore') and the dry_run preview path, which is more than nothing. However, it never states when to use this instead of the adjacent job_stop/job_disable tools or what prerequisites exist.

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