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

Annotations only flag destructiveHint=true; the description adds the substantive reason — this writes records into a connected external SaaS destination, i.e. changes leave the platform. It explains the full-sync escalation too, but omits auth/permission needs, whether duplicate rows can be pushed, and any rate limits or partial-failure behavior.

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?

Two tight sentences front-loaded with the action and its blast radius, followed by the one parameter flag that changes behavior. No filler and no repetition of the title.

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 2-param mutation with no output schema and only a destructiveHint annotation, the description covers the essentials: what is triggered, what it writes to, and how to widen the scope. Missing only the post-trigger behavior (returned run id, how to track completion), which mildly limits an agent orchestrating a multi-step sync flow.

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 in the schema. The description's force_full_sync phrasing ('re-sync all rows instead of just changes') is essentially a restatement of the schema description, adding no new syntax, constraints, or defaults; baseline 3 applies.

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 ('TRIGGERS a sync run for the given sync id') and immediately qualifies the effect as a live write into the destination SaaS tool. That distinguishes it from every read-only sibling (census_get_sync, census_list_sync_runs, census_get_sync_run) without opening a schema.

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 invocation context — use this to kick off a live sync, with force_full_sync=true as the alternate mode for re-syncing all rows. It never names a sibling or an exclusion (e.g. 'use census_get_sync_run to poll status afterwards'), so routing to it vs. the read tools is left partly to inference.

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