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

Annotations already flag readOnlyHint=false and destructiveHint=false; the description adds the important behavioral context that this only changes the caller's own notification choice and grants no new data access ('numbers they are already allowed to look at'). It doesn't describe post-subscription effects such as confirmation or delivery timing, but those are reasonably covered by the schema's channel description.

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 two short sentences with no filler; the key permission/scope constraint is front-loaded and the second sentence clarifies that this is about notifications on already-visible data. Every sentence adds information not present in the title or schema.

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 tool with a rich input schema and output schema, the description covers the non-obvious permission and scope aspects, which are the main things an agent could not infer. The only real gap is the lack of explicit routing guidance such as 'check get_digest to see current subscription' or 'do not use for team-level changes'.

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 100%, so the input schema already documents mcp, channels, and subscribed thoroughly, including defaults and the fact that channels are ignored when unsubscribing. The description's 'choosing what they receive' adds only a light thematic gloss rather than semantic detail beyond the schema.

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 title explicitly says 'Subscribe or unsubscribe from a digest' and the description adds that the operation is scoped to the caller's own subscription ('set their own'), so the action and resource are clear. It does not explicitly contrast with sibling tools like get_digest, but the title alone distinguishes them.

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 an implied usage context: anyone with read access to the MCP may change their own digest ('Anyone who can read the MCP may set their own'), which signals a self-service action. It never states when to prefer this over get_digest or create_alert, nor when not to use it.

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