grokbot_draft

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

No annotations are provided, so the description carries the full burden. For a tool whose name says 'draft' but whose text says 'send', the agent cannot tell whether a real message is delivered immediately, whether the draft remains pending, what permissions are needed, or what side effects occur — all material for a mutation with zero structured coverage.

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?

Two short sentences, front-loaded with the action and immediately followed by the constraint; there is no filler. It is a little terse for a tool with two nested object shapes, but nothing is wasted.

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 tool with nested objects, five parameters, no annotations, and no output schema, the description omits what happens on success, whether the draft is delivered or queued, and how agent_id/entry_id are consumed. It is not complete enough for an agent to invoke confidently without inspecting the schema.

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 60% and the mutual-exclusion rule between email and slack is real added meaning not expressed in the schema (which only marks agent_id/entry_id as required). But agent_id, entry_id, and session_id remain undocumented in both places, so the description only partly compensates.

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 verb+resource pair is stated (send a draft), but 'draft' conflicts with 'send' — it is unclear whether this dispatches a queued draft or creates a pending one, especially with the sibling grokbot_discard_draft implying drafts are artifacts to be resolved later. No differentiation from the sibling grokbot_send is given, leaving the agent to guess which one to pick.

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?

'Exactly one of email or slack is required' is a genuine invocation rule that constrains how to call it. However, there is no when-to-use guidance relative to grokbot_send or grokbot_discard_draft, and no prerequisites (e.g. whether an agent_id must be running) are mentioned.

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