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

Annotations already establish readOnly, idempotent, non-destructive behavior, so the description only needs to add edge-case context, and it does: it explains that selectable ignores suppression, other campaigns and cooldowns, and that total counts unselectable contacts. Those caveats materially change how an agent would interpret results. It does not cover pagination limits or ordering, 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?

Three sentences, front-loaded with the purpose, then two tight caveat clauses about selectable and total. No filler, but the caveat sentences are dense and would read better as distinct points.

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?

There is no output schema, so the description must convey return shape, and it does name the key fields (per-contact email/LinkedIn availability, selectable, total). For a single nested query parameter with no writes, this is close to sufficient; the main omission is any explanation of filter syntax.

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 reported at 0%, so the description needs to carry parameter meaning, and it largely does not. It implies paging (limit/offset) and destination-based filtering (email vs LinkedIn), but never explains the search string, the JSON-encoded filters format, or the four destination_requirement enum values.

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: "Searches and pages through workspace contacts available for a campaign audience," which tells an agent this is a read/search over audience-eligible contacts. It distinguishes itself from plain contact listing by the audience scoping, but never names how it differs from close siblings like listCampaignContacts or previewCampaignAudience.

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?

Usage is implied by "available for a campaign audience" and by the paging language, so an agent can infer this is for browsing audience candidates. There is no explicit when-to-use guidance and no mention of when to prefer previewAudience, checkAudienceAvailability, or listCampaignContacts instead.

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