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

Goes meaningfully beyond the annotations by disclosing the effect boundary: campaign and broadcast mail is suppressed 'until it resubscribes' while transactional mail keeps flowing. That reversibility and channel-scoping is exactly the kind of context annotations cannot express. It says nothing about whether a contact record is modified or what happens if the address was never subscribed.

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?

Three short sentences, front-loaded with the effect, then the exception, then the when-to-use cue. No restatement of the name or title and no wasted clauses.

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 two-parameter mutation with no output schema, the important behavioral facts — suppression scope, transactional carve-out, reversibility — are all present. The remaining gap is the response shape and any idempotency note (annotations mark this non-idempotent, which is unintuitive for an unsubscribe).

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%, so the description carries the burden, and it only partially does — 'from this project' implicitly scopes project_id, and 'an address, contact or not' hints that email need not exist as a contact. It never clarifies email format, case sensitivity, or whether project_id accepts an ID versus a slug.

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 ('Unsubscribe an address') and adds scope precision — 'contact or not' — so an agent knows a non-contact address is a valid target. It does not name the nearest sibling (block_email) to draw the line explicitly, which keeps it short of a 5.

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?

'Use it when a person asks to stop getting marketing email' gives a clear triggering condition tied to a consent request. It offers no exclusion guidance against block_email or resubscribe_email, so the agent must still infer when this is the wrong tool.

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