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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context beyond them: authentication is bound to the original API key and email:read scope, approval is out of reach, no sending or provider calls occur, and no inference credits are consumed. It also warns that unknown delivery outcomes stay unresolved and that provider acceptance does not prove inbox delivery, an open, or a sale — exactly the interpretive caveat an agent needs to avoid overclaiming results.

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 return payload is front-loaded in the first sentence, followed by access restrictions and then the interpretive caveats — a sensible order with no filler. A few phrases ('Zero inference credits', 'native human-review link') are terse jargon that cost a little parsing effort, but every sentence carries distinct information.

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 single-parameter read with an output schema and full annotations, the description covers access scope, mutation limits, and result interpretation thoroughly, so return values need not be re-explained. The one gap is relational: with many similarly named get_* siblings, it never positions itself against the email campaign/report tools.

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%, and send_run_id is documented in the schema as an exact campaign or durable send-run identifier scoped to the authenticated organization. The description implies the same resource ('a frozen plan') but adds no format, lookup, or scoping detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 uses a specific verb ('Read') and enumerates exactly what is returned: the frozen plan, native human-review link, approval reference, and per-recipient delivery counts. That is far more concrete than the title alone. It stops short of naming the sibling tools (get_email_campaign, get_email_report) it must be distinguished from, so an agent choosing among 45 siblings still has to infer the boundary.

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?

Useful constraints are stated: restricted to the original API key and current email:read scope, and 'This tool cannot approve.' Those tell the agent what the tool will not do. However, there is no explicit when-to-use guidance and no named alternative — the description never says whether to reach for get_email_report or get_email_campaign instead, which is the main selection question for this tool.

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