remove_connection

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

With destructiveHint=true already set, the description still adds real information: the pool is closed as a side effect, config-file-backed connections are erased from disk, and environment-defined connections are only dropped for this session. That is exactly the scope-of-destruction detail an agent needs before invoking a destructive tool.

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?

One front-loaded sentence with a parenthetical for the conditional side effects; every clause adds a distinct fact (pool closed, file deleted, env-only session removal).

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 and annotations flag destructiveness, so the description only needed to explain the mutation's scope, which it does thoroughly. The only gap is that it never contrasts with close_connection, leaving a plausible ambiguity for an agent choosing between them.

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?

There is a single parameter and schema coverage is 100% ('Nome ou alias da conexão a remover'), so the schema already carries the semantics; the description adds nothing about accepted name vs. alias forms. Baseline 3 is appropriate.

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 ('remove a connection from the registry') and enumerates concrete effects: closes the pool and, when the connection came from the config file, deletes it there. That distinguishes it from list_connections and add_connection, but it never names close_connection, the sibling whose overlap (pool closing) most needs differentiation.

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 parenthetical clarifies that env-var-based (.mcp.json) connections only leave the current session, which implies when removal is not persistent, but there is no explicit when-to-use vs. close_connection or reload_connections guidance.

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