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

Annotations already flag destructiveHint=true, idempotentHint=false, openWorldHint=true, and the description corroborates this by explaining that wasSent=false actually sends the email again. It also adds a policy the annotations cannot express — always defer to the owner rather than guessing — which is valuable for a destructive, non-idempotent call. It does not address duplicate-send risk or what state the record ends in.

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?

Three short sentences with the trigger condition first, the two outcomes second, and the guardrail last — no filler. Slightly terse given the destructive nature of the tool, but well front-loaded.

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 two-parameter, destructive resolution tool with annotations covering safety and no output schema, the description supplies the essential missing layer: the real-world context (owner checks Sent folder) and the consequence of each branch. The main residual gap is identifying which email messageId refers to and any follow-up state change.

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 50%: the schema already spells out wasSent ('true if the email went out, false to send it again'), and the description largely restates that. messageId is undocumented in both places, though its role is inferable from the situation described. Baseline 3 is appropriate given the partial overlap with structured data.

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 makes clear this settles an email stuck in a 'being checked' state, with wasSent=true recording it as sent and wasSent=false re-sending it. The verb is implicit ('settle'/'resolve') rather than stated outright, and no sibling (e.g. soclo_leads_outcome, soclo_leads_linkedin_sent) is named for contrast, but an agent can infer the operation.

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?

The opening clause 'When an email is being checked' gives a clear triggering condition, and 'Never choose for the owner' is an explicit usage constraint. It stops short of naming alternatives or stating what to do if the owner cannot confirm, so it is strong context rather than full routing guidance.

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