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

Annotations already flag destructiveHint=true, openWorldHint=true and idempotentHint=false; the description adds the key side effect — pending follow-ups stop — and Gmail-specific semantics, which the annotations cannot express. It still omits whether an existing outcome can be overwritten and that a repeat call is not idempotent, which matters for a destructive write.

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?

Front-loaded with the action and its consequences in three short sentences. Slight redundancy: the outcome list restates the enum and 'On Gmail this is how a reply stops the follow-ups' repeats 'Pending follow-ups stop'.

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 mutation with no output schema, the description covers what to record, why it matters, and the side effect on follow-ups — enough to call it correctly. Missing are re-record/overwrite behaviour and any permission or account prerequisites, which are the remaining gaps.

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?

Only 50% of the schema is documented (outcome has a description and enum; leadId has neither), so the description should compensate. It does enumerate the four outcomes in prose, matching the enum, but adds no guidance on leadId (where to get it, valid UUID) or what an invalid/unknown lead id does.

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?

States a concrete verb ('Record') plus the domain object (a lead outcome) and enumerates the four possible values matching the enum, so an agent knows exactly what the tool writes. It does not name-differentiate from neighbouring lead tools like soclo_leads_reject or soclo_leads_suppress, which also terminate outreach, so the boundary is left implicit.

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?

Gives an explicit trigger ('record it as soon as the owner says they replied') and the reason to act promptly (follow-ups stop). It does not say when NOT to use it or point to alternatives such as suppress/reject for opt-outs, so routing between similar lead-state tools remains guesswork.

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