conduyt_ai_improve_email

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

No annotations are provided, so the description carries the full disclosure burden, and it omits the key behavioral facts: whether this only returns text or mutates a stored draft, whether anything is sent, and whether the result is persisted anywhere. It does convey the transformation scope (body rewritten, subject conditionally), but for an AI generation tool with zero annotation coverage that is thin.

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, front-loaded with the action and with zero filler. Slight redundancy between the opening sentence and the rewrite description, and the inaccurate 'optionally the subject' phrasing costs a point.

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 an AI text-transform tool with no annotations and no output schema, the description should state what comes back (rewritten body only, or body plus subject) and whether the original draft is touched. Neither is covered, and the required-subject mismatch leaves the contract ambiguous.

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%, so the baseline is 3; the one extra note, 'Pass instructions to steer the rewrite', reinforces the instructions parameter but adds nothing the schema example doesn't already convey. The description actively muddies things by calling the subject 'optional' while the schema lists it as required.

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?

A specific verb plus resource ('Improve an email draft', 'Rewrites the body ... for clarity, tone, and persuasiveness') tells an agent exactly what it does. It never distinguishes itself from the nearby siblings conduyt_ai_compose_email and conduyt_reply_suggestion, which also produce email text, so the agent must infer the boundary.

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?

'Improve an email draft' implies the usage condition—an existing draft rather than a blank compose—but the description never says so explicitly and offers no when-not guidance. With conduyt_ai_compose_email, conduyt_send_email, and conduyt_reply_suggestion in the same family, the routing decision is left to inference.

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