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

Annotations only supply destructiveHint=false, so the description carries the real behavioral burden: it is a two-phase operation ('nothing changes until confirm_action'), requires an authenticated unlocked session, and explains how replaces_proposal_uid supersedes an old proposal. This is consistent with the safe/non-destructive annotation.

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?

Front-loaded with the core action and scope, then prerequisites. It is dense at six sentences and slightly repetitive about vesting/partial cancellation, but nearly every clause carries operational information rather than filler.

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?

With no output schema, the description still gives an agent everything needed to call correctly: the proposal-only nature, the confirm_action follow-up, the unlock prerequisite, the stop_vesting dependency, and the replace-a-proposal mechanism. Nothing material is missing for a six-parameter mutation-like tool.

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 coverage is already 100%, so the baseline is 3, but the description adds logic the field-level text doesn't fully convey: whole-holding cancellation is always permitted while partial cancellation depends on vesting state, and take_from only matters when the holding is partly vested and vesting has stopped. That conditional framing adds real meaning about how quantity and take_from interact.

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 and resource ('proposes cancelling shares or options from one holding') with concrete examples (leaver forfeiture, company cancellation), and clarifies the tool's output is a proposal rather than a mutation. An agent can distinguish it from siblings like stop_vesting or confirm_action immediately.

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?

Explicitly states when partial cancellation is allowed and when it is not, names the alternative (use stop_vesting first), and gives the required precondition (unlock_shareflo must have been called). This is textbook when/when-not/alternative guidance.

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