capability_add

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

With no annotations, the description carries the full burden, and it does disclose two valuable traits: the server becomes live immediately and its tools are exposed as '<alias>__<tool>'. It says nothing about whether the install persists across restarts, what happens on a bad identifier or unreachable command, whether it is idempotent when adding the same server twice, or what permissions/network access are required for a mutation of this kind.

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?

Three short sentences, front-loaded with the action, then the parameter semantics, then the observable effect. No filler, and the parenthetical cross-reference to capability_search is placed exactly where the agent would need it.

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 needn't be explained, and the core semantics are covered for a two-parameter tool. But this is an unannotated state-mutating operation: persistence, failure behavior, and the interaction with capability_remove/capability_list (does the new server show up there?) are all unaddressed.

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 0%, so the description must compensate, and it handles the required `identifier` thoroughly — both accepted forms with literal examples. The `alias` parameter is only conveyed indirectly via the '<alias>__<tool>' naming template; the description never says what happens when alias is omitted/null or whether it must be unique.

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?

"Install and mount an MCP server" is a specific verb+resource pair, and the description immediately distinguishes the two identifier modes (registry name vs local stdio command). It also explicitly points at capability_search for the registry-name case, so the agent can separate this from its siblings without opening schemas.

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 description names the condition for one path ("see capability_search" when you need a registry name) and shows a concrete local-command form, which is clear usage context. It stops short of stating when to use capability_add versus capability_consider or capability_verify, or any prerequisite/ordering (e.g. search first, consider before add).

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