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

Annotations declare destructiveHint=true and readOnlyHint=false, which alone would alarm an agent about a write. The description adds the crucial bound: the draft 'stays in the approval queue, and this tool sends nothing', so the agent understands the mutation is a text replacement, not an outbound message. It does not cover auth/permission requirements or whether the prior text is recoverable, which keeps it short of a 5.

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?

Four sentences, all front-loaded with the core mutation first, then sourcing, then side effects, then the exclusion. No filler, though the middle two sentences pack several cross-references that could be trimmed.

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?

An output schema exists, so return values need no explanation. The description covers the operation, data sourcing from two siblings, the side-effect boundary (nothing sent, stays queued), and the unsupported draft kind with its alternative — everything needed to invoke correctly.

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%, and the schema itself already documents the text/draftText/confirmText aliasing, the leadId source, and the subject null-vs-omitted behavior in detail. The description's parameter-relevant content (leadId from list_pending_outreach, scoreExplanation source) largely repeats what the schema states, so baseline 3 applies.

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?

Specific verb ('Replaces the text') plus resource ('an outreach draft') plus a state qualifier ('waiting for approval') that an agent can verify. It clearly distinguishes itself from list_pending_outreach (source of the draft), get_lead_memo (research), and send_outreach (the actual send).

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?

Explicitly routes the agent: current draft and scoreExplanation come from list_pending_outreach, richer research from get_lead_memo, and LinkedIn follow_up drafts are excluded with the correct alternative path (edit in Onsa or approve as written with send_outreach). Both when-to-use and when-not-to-use are stated.

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