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

Annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) already convey the mutation/safety profile. The description adds genuinely useful operational context - idempotency/retry-key handling, canonicality (trust actual_tool_output rather than issuing a state-recovery call), and the confirmation boundary - which goes beyond the annotations. However, much of it is generic server-wide boilerplate rather than tool-specific disclosure.

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 purpose is front-loaded correctly in the first sentence, but the following three sentences are long, reusable boilerplate about canonicality, idempotency, and confirmation that dilute the signal. Appropriate overall length, but a poor signal-to-boilerplate ratio.

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 4-parameter mutation tool with a nested context object and no output schema, the description does cover prerequisites, retry semantics, and how to treat the returned output - enough for an agent to invoke it safely. The vague "every prerequisite stated above" phrasing is the main gap.

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 75%, with each of the three meaningful parameters (senderLocalPart, senderDisplayName, replyToEmail) already documented in the schema including defaults. The description merely enumerates the same fields without adding format, validation, or interaction semantics, so baseline 3 applies.

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 ("Change") and resource (sender local part, display name, reply-to for Corply-sent company mail), which cleanly separates it from domain/inbox siblings like connect_email_domain or enable_company_inboxes. It stops short of naming a specific alternative, so it is clear but not maximally discriminating.

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 only usage signal is "authenticated active company access plus every prerequisite stated above," which is a dangling reference to text not present in this definition. No when-to-use, when-not-to-use, or alternative tool is named, so the agent must infer context from the name alone.

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