draft_follow_up

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

No annotations are provided, so the description carries the load. It usefully reveals the data sources it pulls from and that it 'drafts' rather than sends, which is a meaningful behavioral distinction. However, it is silent on whether the draft is persisted, whether it overwrites a prior draft, and what permissions or preconditions are needed.

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?

A single front-loaded sentence with no redundant wording; the core action and its data source come first.

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?

An output schema exists, so return values need not be explained, and the tool's surface is small. For a drafting tool that plausibly creates a stored artifact, though, it should say whether a draft record is created and how tone can be varied, which it does not.

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 0%, so the description must compensate. It echoes the default 'gentle' tone but never refers to the tone parameter as configurable or indicates any valid values (there is no enum), and it does not clarify that app_id is an application identifier sourced from list_applications. It adds partial meaning but leaves the optional parameter effectively undocumented.

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 (draft a follow-up email) with an explicit scope limit of one application, plus the data source (stored notes and contacts). It is clearly distinguishable from siblings like add_application, set_status, or find_stale_applications, though it does not name them.

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?

Usage is only implied by the name and the 'one application' scoping; there is no explicit statement of when to prefer this over manually writing a follow-up or when it is inappropriate (e.g., application already closed or rejected). No prerequisites are mentioned, such as whether the application must already have contacts or notes.

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