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

The annotations already cover the safety profile (non-destructive, idempotent, mutation, closed-world), so this dimension's bar is lower. The description adds genuinely non-annotated context: 'No charge' discloses that approval has no billing cost, and 'one draft per item copy' constrains how many references are set per copy.

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?

Three short sentences with zero filler; the billing note is front-loaded and the prerequisite follows. It is efficiently sized, though the phrasing of the core action is slightly oblique rather than crisp.

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?

This is a mutating batch tool accepting up to 40 approvals with three sub-fields each, no output schema, and 0% parameter coverage. The description omits what happens on re-approval or whether an approved reference can be replaced, and says nothing about the result of a batch call, which is a substantial gap for a tool of this complexity.

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 0% and the tool takes a nested approvals array with itemId, outputId, and copy fields, all undocumented in the schema. The description partially compensates by explaining where outputId comes from and hinting at the copy concept ('one draft per item copy'), but projectId, itemId, and the copy index range remain unexplained, leaving most parameters semantically opaque.

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?

The description states it marks a draft as the reference for the final, which conveys a specific approval action, and the title clarifies it as approving drafts. However, the phrasing 'marks one draft per item copy as the reference its final is made from' is jargon-heavy and the connection to the verb 'approve' is only implicit, so an agent must infer the operation rather than read it directly.

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?

'Use the outputId shown by get_status' gives an explicit prerequisite and names the sibling that produces the required value, which is a useful routing cue. It stops short of explaining when to approve versus when to use draft or generate, and offers no exclusion guidance, so usage is only partially scoped.

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