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

Annotations already declare idempotentHint=true, destructiveHint=false and readOnlyHint=false, and the description meaningfully extends this by explaining exactly what idempotency means here (same key + same input returns the first result instead of repeating) and by confirming nothing is sent. The remaining gap is whether the 'saved snapshot' persists and appears in listAudiences, which an agent needs to know before calling it on the path to createAudience.

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, front-loaded with what the tool produces and its return values, then the safety reassurance, then the retry contract. No filler and every sentence adds information an agent would otherwise have to guess.

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?

Given a deeply nested body schema and no output schema, the description does the important work of summarizing the return value as admitted/excluded/eligibility counts and covering idempotency. It falls slightly short on whether the snapshot is persisted and how this preview differs from the create path.

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 50% - only available_again and idempotencyKey are documented in the schema. The description compensates partially by mapping the source arrays ('requests, ICPs, companies, contacts or the pipeline') to request_ids, icp_ids, company_card_ids, lead_ids and include_pipeline, but filter fields, destination_requirement, new_only and recontact_lead_id get no added meaning. That lands at the baseline 3.

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 specific verb and resource: builds a saved audience snapshot from requests, ICPs, companies, contacts or the pipeline, plus what it returns (admitted, excluded, eligibility counts). It is clearly distinguishable from createAudience by the word 'snapshot' and 'Nothing is sent', though it never names the sibling it replaces or how it relates to createAudience.

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?

'Nothing is sent' and 'snapshot' strongly imply a dry-run/preflight use before committing a real audience, so usage is inferable. However, there is no explicit when-to-use versus createAudience, saveLeadEngineAudience, previewCampaignAudience, or checkAudienceAvailability, and no stated exclusions or prerequisites.

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