Kill a terminal session

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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds real consequence detail beyond that: the shell and any programs running in the pane are terminated, which tells the agent the blast radius extends past the session object.

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 tight sentences, keyed on the parameter name, with the destructive consequence placed immediately after the invocation rule. Nothing redundant.

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 destructive two-parameter tool with full schema coverage and no output schema, the description covers selection and effect. Minor gaps remain: whether a missing session name errors, how a nonexistent session is handled, and whether running tasks are also affected.

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 coverage is 100%, so both parameters are already documented; the description adds the framing that 'session' and 'all' are alternative modes rather than combinable filters, which is meaning beyond the flat schema.

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 and resource ('Kill one terminal session by name') plus the alternate bulk mode, which cleanly distinguishes it from terminal_create, terminal_write, terminal_read and terminal_resize among the siblings.

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?

The two invocation modes are spelled out — name a session, or set all=true to kill everything — so an agent knows how to select behavior. It stops short of warning when not to use it (e.g. neither parameter supplied, or preferring task_stop for running tasks), so no explicit exclusions.

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