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

Annotations already declare the write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's marginal job is behavior beyond that. It does add two useful facts: reminders are generated before the notice date, and the operation needs confirmation. It does not say what happens to existing fields when terms are replaced — full overwrite vs merge — which matters most for an update path that is explicitly not idempotent.

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?

Four short sentences, front-loaded with purpose and the create/replace fork. The parenthetical '(agreement_id from vendors view agreements)' is compact but slightly telegraphic; otherwise no wasted text.

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 mutating tool with an output schema (so return values need not be described), the description covers required vs optional inputs, the update handle, a side effect (reminders) and a confirmation requirement. The remaining gap is replace semantics on existing fields.

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?

Top-level schema coverage is effectively 0% for terms/agreement_id, so the description must compensate, and it does: it separates the minimal required set (vendor and dates) from the optional set (commitment, tiers, notice, overage) and sources agreement_id. It omits semantics for several optional fields such as covers, overage_pct and price_new_spend, which remain only in the nested schema.

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 ('Records an AI vendor agreement') and additionally names the replace/update mode keyed on agreement_id. An agent can distinguish it from sibling tools like set_contract and vendors without opening the 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 the create-vs-replace condition (pass agreement_id to replace existing terms) and points at where that id comes from ('vendors view agreements'). 'Confirm first' adds a workflow precondition. No explicit when-not or named alternative beyond the pointer to vendors.

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