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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds that this books a loan, requires named-approver confirmation, and explicitly does not send, bind, sign, or wire. It does not cover idempotency or reversibility, but it provides meaningful behavioral context beyond the annotations.

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 the action and precondition, followed by boundaries and a prerequisite. Fragments and jargon like 'Compact-10' are terse but purposeful, with little 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 two-parameter mutation with full schema descriptions and non-destructive annotations, it covers the key precondition, authorization requirement, and scope limits. Minor gaps remain around return behavior and failure modes, but the core invocation guidance is present.

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 100%, including descriptions for caseId and confirmed, so the baseline is 3. The description reinforces confirmed=true and the named-approver condition but adds no syntax or meaning beyond what the schema already provides.

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?

Uses a specific verb ('Book') and resource ('approved file as a loan'), with explicit preconditions and boundaries. The reference to a staged term sheet for Compact-10 APPROVED helps distinguish this from sibling tools such as stage_term_sheet.

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?

States the operative condition clearly: only after confirmed=true and only by the named approver. It also lists non-actions ('does not send, bind, sign, or wire') and a Compact-10 prerequisite, but does not explicitly name a sibling alternative or say when not to use it.

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