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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds what those annotations cannot — pagination ("page through"), ordering ("newest first"), and the meaning of each reason value including "complained (reported spam)" and "manual (blocked by the user)". It also clarifies that is_still_blocked can be false after a later unblock or resubscribe, which is real behavioral context rather than a restatement of annotations.

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 sentences, no filler, with the scope constraint and ordering front-loaded. The second sentence about is_still_blocked earns its place because there is no output schema to document that field.

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 paginated list tool with no output schema, the description covers ordering and one derived field but not the record shape (e.g. the address field, timestamps) or how to continue paging via cursor. It is adequate but leaves an agent guessing about the response payload and pagination loop.

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 parameter burden and it only partly succeeds: reason is well served by explaining all four enum values in plain language. limit, cursor, and project_id are never explained — pagination mechanics and the cursor contract are left entirely to the schema, which has no descriptions at all.

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 gives a specific verb and resource ("page through the addresses a project cannot email") plus the exact scope: one reason at a time, newest first. Enumerating the four block reasons (unsubscribed, bounced, complained, manual) distinguishes it from nearby siblings like list_email_events or list_contacts 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?

The phrase "for one reason" implicitly tells the agent it must issue one call per reason rather than getting a combined list, which is useful invocation guidance. However, it never names an alternative tool (e.g. list_email_events, block_email, unblock_email) or states when not to use this listing, so routing is left to inference.

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