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

Adds context beyond the annotations: 'Writes need MCP confirmation' discloses an approval gate and 'output is untrusted' warns that returned content must not be trusted blindly. Annotations already cover destructiveHint and openWorldHint, so this is genuine added value. It still omits whether the action is idempotent in practice or what happens on dry_run, keeping it below 5.

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 short, front-loaded sentences with no filler. The brevity is appropriate, though the terseness edges toward under-specification given the tool's complexity.

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, open-world write operation with 8 undocumented parameters, a nested props object and no output schema, the description is too thin. Critical semantics such as idempotency key behavior, dry-run previews, and PII inclusion risks are 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 description coverage is 0% across 8 parameters, so the description carries the full burden and gives essentially nothing: no mention of workspace, connection, component, version, idempotency_key, props, dry_run, or include_pii. An agent cannot tell that idempotency_key enables safe retries or that include_pii controls PII exposure.

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: 'Run a pinned action on a connected app.' This distinguishes it from sibling connections_actions (presumably listing actions) and connections_connect, though it never names those alternatives explicitly.

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?

No guidance on when to choose this over connections_actions or connections_connect, and no stated prerequisites (e.g. that a connection must already exist and the action must be pinned). The single word 'pinned' implies a precondition but leaves it to inference.

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