add_terminal

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses the persistent side effect (writes terminals.toml), explicitly bounds the scope (no copy, no install created), and describes an input-validation refusal rule. It omits duplicate/overwrite behavior and error surfacing, which are the main remaining behavioral unknowns for a registry write.

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?

Four short sentences, each earning its place: what it does, what it writes, what it does not do, and the id rule, followed by the junction constraint. The write side effect is front-loaded rather than buried.

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 7-parameter mutation with no output schema and zero schema descriptions, the definition should identify at least the identity-critical fields (terminal_id vs name, enabled, role). It covers the file target and one refusal rule but leaves most of the argument surface unexplained for an agent trying to construct a valid call.

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% across 7 parameters, so the description carries the full burden, yet it only explains `name` (becomes the registry id when set) and implies `path`. The meaning of role, login, server, enabled, and terminal_id is left entirely undocumented in both schema and description.

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 gives a specific verb and resource ("Add ... to the registry") and names the concrete artifact it mutates (terminals.toml), which clearly separates it from list_terminals and remove_terminal. It stops short of explicitly naming a sibling it could be confused with, but the action is unambiguous.

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 two accepted inputs (a discovered terminal or a path) and gives an actionable redirect for the failure case: a junction to an install is refused, so the agent should register the real directory instead. It does not cover ordering relative to launch_terminal/use_terminal or what to do if the id already exists.

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