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

Annotations already declare destructive=true, openWorldHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuine context beyond them by naming the exact state transition the operation triggers, which tells the agent what the side effect is rather than just that one exists.

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 tight sentences with no filler. The action and its state transition come first, with the precondition second — well front-loaded.

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 mutation tool with annotations covering the safety profile and no output schema, the description supplies the two things that matter most: the precondition and the resulting state. It could go further on failure modes (e.g. what happens if the agreement is not in draft), but it is largely sufficient.

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?

There is a single UUID path parameter, and the description's 'draft agreement' wording reinforces that the id must reference a draft. The schema already carries a description for the id field, so the description adds only marginal meaning. Baseline 3 for a one-parameter tool whose schema does most of the work.

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 (send) and resource (draft agreement) plus the recipient, and the state transition '(draft → sent_waiting_for_initial_review)' makes it distinguishable from siblings like resend-agreement-email and void-agreement. It stops short of naming any sibling explicitly, so it is clear but not fully self-differentiating.

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 precondition 'Agreement must be in draft status' tells the agent when this call is valid, which is useful. However it does not contrast with the obvious alternative 'resend-agreement-email' for agreements already sent, leaving the choice between the two to inference.

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