field_coverage

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

No annotations are supplied, so the description carries the full burden, and it does well: it discloses what the tool computes (populated fraction, date span), that it emits a warning on recent-window patterns, and that a display name produces an actionable error listing real field names. It never states read-only status or cost/latency characteristics, which are the remaining behavioral gaps.

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 front-loaded with the core action and the 'recent-window trap' framing, then the return shape, then the imperative usage rule, then the input constraint. Each sentence carries information, though the parenthetical balance example and the framing clause make it slightly denser than strictly necessary.

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?

An output schema exists, so return values need not be explained, yet the description still covers the key ones and adds the error contract. Completeness is only weakened by the undocumented 'date_field' parameter and by not clarifying how dataset_id is obtained (e.g. via list_cached_datasets).

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 0%, so the description must compensate. It richly documents 'field' (must be a machine name from columns_field_name, display names error out) and implies 'dataset_id' must reference a cached dataset, but 'date_field' is never mentioned at all, leaving one of three parameters with no semantics anywhere.

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?

The description names a specific verb and resource: probe how ONE field is populated across a cached dataset, and it explicitly reports the populated fraction plus the date range of populated rows. The capitalized 'ONE field' scopes it clearly against the dataset-level sibling coverage_audit, so an agent can tell them apart without opening either 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?

It gives an explicit trigger: 'Always run this before summing or rate-computing over a field', which tells the agent exactly when this tool is required. It does not name when-not-to-use cases or point to a specific alternative for whole-dataset checks, so it stops short of full routing guidance.

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