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

Annotations only declare destructiveHint=false, so the description carries the real burden and does: it discloses that this is proposal-only with no mutation until confirm_action, that unlock_shareflo is a prerequisite, and that Shareflo computes vested amounts from the schedule and surfaces them in the proposal. That is substantive behavior beyond the structured fields.

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?

Five sentences, each load-bearing: purpose, computed-value behavior, the override constraint, the confirmation gate, and the auth prerequisite. The most important constraint (no effect until confirm_action) is placed prominently.

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 6-param proposal tool with no output schema, the description covers the full operating picture: what is computed, what is deferred, what must precede it, and where the notes requirement applies. An agent can invoke this correctly without further inference.

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 100%, so 3 is the baseline, but the description adds actionable semantics the schema only partially conveys: the override parameter is a deliberate exception requiring explicit user instruction, and the notes field becomes mandatory in that case. It reinforces rather than duplicates the schema's own parameter docs.

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+resource ("Proposes stopping vesting on one holding of shares or options") plus the typical trigger (employee leaving). This clearly differentiates it from siblings like amend_vesting or cancel_shares_or_options without needing to open any schema.

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?

Gives explicit when/when-not guidance for the override path ("Normally you should not provide an overridden_vested_amount; only do so if the user specifically asks"), plus two prerequisites: nothing happens until confirm_action, and unlock_shareflo must run first. It names the exact sibling tools that gate this operation.

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