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

With no annotations, the description carries full behavioral burden and does well: it discloses auth requirements, real-observed-change semantics, event types, return payload (watch id + HMAC secret), signature header format, and free/pro tier limits. However, its 'Fires only on ...' list omits tools_changed, which is a valid event in the schema, so transparency is slightly incomplete.

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?

The description is six short sentences, each earning its place: purpose, event types, auth, delivery choice, return value, and rate limits. It is front-loaded and contains no filler.

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 subscription tool with no output schema, it covers the return value, signature verification hint, auth, delivery method, event types, and tier limits. The main gaps are the omitted tools_changed event and the lack of an explicit 'provide at least one of webhook_url or email' requirement.

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 adds only delivery preference (webhook over email) and optionality, which is useful but does not meaningfully expand parameter meaning beyond what the schema already explains.

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 opening sentence states a specific verb and object: 'Subscribe this agent (or a human email) to alerts for ONE specific MCP server.' It also names the exact event types and scope, making it immediately distinguishable from census_watch_list and census_watch_unsubscribe.

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 gives actionable guidance: prefer webhook_url (https) to receive POST callbacks, treats email as optional, and notes that x-api-key is required. It does not explicitly name alternatives such as census_watch_list or state that at least one delivery endpoint should be provided, so guidance is strong but not exhaustive.

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