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

Discloses behavior far beyond the annotations: nobody on the drop is marked and no count or state changes, which reconciles why destructiveHint is false while readOnlyHint is also false (an email is still emitted). It enumerates skip outcomes (missing_tags, a link switched off), refusal codes with their details payloads (plan_limit/upgradeUrl, gmail_not_connected/connectUrl, rate_limited with dry_run_daily_limit or gmail_daily_limit, not_found), the no-Cc rule, and the fact that titles and viewer-supplied text are untrusted author-written content. No annotation contradiction.

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?

It is a single dense block, but it is front-loaded: the what (dry run to the owner's Gmail) and the identifying detail (contactId default) arrive in the first two sentences. Nearly every later sentence carries distinct decision-relevant information (quota, skip paths, refusal codes), though the lead-in explanation of what a drop is could be trimmed for callers who already know the domain.

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 side-effecting send with no output schema, the description supplies everything an agent needs: permissions, quota cost, template version selection, default parameter behavior, skip semantics, and a full refusal taxonomy. Nothing material about calling it correctly is left undocumented.

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 100%, so both parameters are already documented; the description still adds operational meaning by stating contactId selects the person and defaults to the first in send order, and that campaignId is the drop's id. It adds little on the 24-hex format beyond the schema, but the default-selection semantics are worth having in prose.

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?

Opens with a concrete verb+resource: sends one person's email of a drop, rendered as the drop renders it, to the owner's own Gmail as a dry run. It even disambiguates the domain vocabulary ('a drop (a campaign in the API)'), which helps separate it from campaign tooling. It stops short of naming the sibling dry-run tools (lnkdrp_dry_run_campaign, lnkdrp_dry_run_email) or lnkdrp_send_drop, so the agent must infer the choice from context rather than being routed explicitly.

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 clear conditions for correct invocation: the drop's owner must call it (forbidden otherwise), contactId defaults to the first person in send order, and pre-Send uses the published template while post-Send uses the frozen version. It also sets expectations that dry runs consume quota (25 per 24h, 50 Gmail sends). What it lacks is an explicit 'use X instead when...' clause pointing at the real send or the other dry-run variants.

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