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

Annotations already cover readOnly, idempotent, and non-destructive, so the bar is lower; the description still adds real value by clarifying that this is a validation gate that performs no email/post, that only the stored wording is returnable, and what the two outcome states mean.

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?

Short, front-loaded, and every clause carries information (outcome states, refusal rules, non-sending disclaimer). The clipped fragments ('A draft is refused. A suggestion is refused until...') read tersely but remain efficient rather than wasteful.

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?

An output schema exists so return structure needn't be explained, and the description handles the SENDABLE/REFUSED semantics well. However, for a four-parameter tool with zero schema descriptions, the meaning and constraints of kind and libraryId are left entirely unstated, leaving a real 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 0% across four required parameters, so the description must compensate. It partially does: 'exact sentence' maps to text and 'emailed, posted, or quoted' maps to the channel enum, but kind and libraryId are never explained, leaving half the parameters undocumented.

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 states a specific verb ('Check whether') and resource ('an exact sentence may be emailed, posted, or quoted') and explicitly negates the obvious misreading by saying 'This tool does not email or post.' That distinguishes it from the send-flavored siblings, though it never names get_sendable_wording or approve_sendable_wording directly.

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?

It gives concrete decision rules: SENDABLE returns the stored wording with no substitution allowed, REFUSED means do not send, drafts are refused, and suggestions are refused until accepted and approved. It lacks explicit 'use X instead' routing to siblings, but the when/when-not conditions are clear.

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