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

Annotations only declare destructiveHint=false, so the description carries the real burden and does: it discloses the side effect (the row is flagged as waiting on Elliot), the invariant that sends clear both flags, and the access restriction (Internal Coderbuds staff only). It also states a hard capability limit — nothing can be sent from here — that no annotation conveys.

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?

The two most decision-critical facts — staff-only access and the cannot-send division of labour — are front-loaded, and each paragraph addresses a distinct concern (permission, division of labour, content quality, side effects). Slightly long, but there is little filler.

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 3-parameter mutation with no output schema, the description covers everything an agent needs: who may call it, what it writes, what state it sets, what clears that state, and how to handle the failure case (park via update-prospect). Nothing essential is missing.

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 100%, so the baseline is 3; the description goes beyond by adding substantive quality semantics for `draft` — write the message itself, no placeholders, ground every claim in the worklist, state what is unverified. `needs_action_reason` is left entirely to the schema, which is acceptable given it is fully documented there.

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 — save an opener draft against a prospect — and positions it precisely in the workflow (the writing step, as opposed to the sending step). This clearly separates it from record-prospect-outreach-tool (recording an actual send) and update-prospect-tool (parking a row).

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 an explicit when-to-use, an explicit when-not-to (if you can't write an honest opener, use `update-prospect` to park the row with the question), and an explicit boundary (you cannot send; Elliot sends). The routing decision to the sibling is spelled out rather than inferred.

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