upsert_conversation_draft

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

With no annotations, the description carries the full behavioral burden and does real work: it discloses two rejection conditions (blank `content` combined with empty `meta`; `meta` over 32 KB) and an authorization requirement. That is meaningful, non-obvious failure behavior an agent cannot infer. What it omits is the success behavior and response shape, and whether omitting `content` clears an existing draft (partial-update semantics).

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 save/update behavior and the rejection rules are front-loaded, so the first sentence carries the most useful information. The trailing endpoint path and tag line are mild but conventional noise, and the `type` default is stated once more than necessary. No sentence is wasted, though a couple are duplicative.

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 mutation tool with no annotations and no output schema, validation and access rules are well covered, but the description never says what a successful call returns or what state the draft ends in. The 32 KB and blank-content rules are covered; the semantics of a partial save (omitting `content` or `meta`) are not. That is a real gap for an upsert tool.

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 schema already documents all four parameters, including the enum and default. The description restates the `reply` default and the 32 KB bound rather than adding new meaning, though the coupling of blank `content` with empty `meta` as a joint validation rule is genuinely additive. Baseline 3 fits given the schema does the heavy lifting.

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?

"Saves or updates the caller's draft for a conversation" gives a specific verb pair (upsert semantics) and an unambiguous resource (the caller's own draft on one conversation). The name plus this sentence makes the create-vs-update duality explicit, which is the main ambiguity. It stops short of naming the contrast with a sibling like delete_conversation_draft, but 'upsert' plus 'caller's draft' is differentiated enough.

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?

It supplies a precondition ("The caller must have access to the conversation") and a default (`type` is `reply`), which implies the tool is used for both first-save and re-save. However, it never says when to prefer this over a full conversation update or when to reset a draft instead of overwriting it, and there is no explicit when-not guidance.

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