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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the details that actually matter for a secret-issuing tool: the secret is returned exactly once, keys survive disconnection of this MCP session, revocation happens in the web app, and a specific permission ("Manage API keys") is required via an approval screen. It also states a safe-handling procedure (secret manager or git-ignored env file, never commit or print in chat).

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 sentences, front-loaded with purpose, then secret handling, then lifecycle, then the scope caveat and permission. No sentence is padding — each carries a fact an agent would otherwise get wrong (printing the secret in chat, assuming the key dies with the session).

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-shape explanation is not required. What remains — auth/permission requirements, one-time secret exposure, persistence beyond the session, and where to store the value — is all covered, which is exactly the risk surface for a credential-creation tool.

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 the baseline is 3. The description still earns above baseline by linking scope_mode "channels" to channel_slugs with a decision rule (subset of recipients) that the schema's field-level text does not state as explicitly, and by surfacing the name/permission context an agent needs before filling in the parameters.

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 opens with a specific verb and resource ("Create an ActivitySmith API key") and immediately scopes the audience for that key (CI job, server, script). This distinguishes it cleanly from siblings like rename_api_key, delete_api_key, and list_api_keys without needing the schema.

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 gives a concrete conditional rule for the risky parameter: "Use scope_mode 'channels' with channel_slugs only when the key should reach a subset of recipients." That is real when/when-not guidance. It stops short of naming sibling alternatives (e.g., list_api_keys for existing keys), so it falls just under a 5.

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