prepare_outreach

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

Annotations label this non-read-only, non-idempotent, non-destructive. The description adds substantial context beyond them: no server LLM is invoked, no message is sent, draft_mode does not bypass review, context is a bounded subset rather than full history, and opt-outs/activation are rechecked after the browser read. These disclosures meaningfully raise the bar on the annotated safety profile.

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?

Sentences are clipped but front-loaded and each earns its place, covering scope, caveat, side-effect boundaries, and review flow. It is terse to the point of feeling stitched together, but not padded.

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 4-parameter, 3-required mutation-class tool with an output schema, the description covers the key non-obvious behavior: bounded context, no send, review requirement, rechecked eligibility. It omits parameter meaning for account/profile, but the critical operational and safety context is present.

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 0%, so the description carries the full parameter burden. It explicitly defines the semantics of message_text ('your exact supplied text') and mentions a 10-post cap, but account, profile, and the default post_limit of 5 are never explained, leaving half the surface ambiguous.

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 description bundles three actions (fetch profile, fetch posts, create draft) at unspecified granularity, making it hard to tell whether this is a research tool or a preparation tool. It doesn't distinguish itself from siblings like get_profile_context, preview_campaign_message, or prepare_reply.

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 gives clear when-to-use guidance by naming get_profile_context as the research step to run first, and it states that the user must review then call approve_draft individually. What's missing is when to choose this over the many other prepare_* siblings.

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