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

Beyond the readOnlyHint=true annotation, the description discloses crucial behavior: the exact four-verdict enum (no_conflict_found, conflict_found, ask_one_question, couldnt_verify), the return payload shape (typed hits, source kind, read date), the auth requirement, and the semantic guardrails 'Unknown counts as no' and 'safe is never used.' These prevent agents from misinterpreting results — exactly what behavioral transparency should provide.

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?

Four sentences each earn their place: purpose, auth prerequisite, return contract, and the two critical caveats. The content is dense but organized as a logical progression, front-loading the core purpose before the operational details. Slightly heavy text density prevents a 5.

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 moderately complex tool with nested objects and no output schema, the description compensates well by enumerating the four verdicts and return fields. Combined with a rich input schema and readOnly annotation, almost everything needed to call correctly is present. Minor omissions like error behavior or rate limits are acceptable at this complexity.

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 67%, above the 50% threshold, so the baseline of 3 applies. The schema itself richly documents subject.kind, venue, thresholds, and restrictions; the description adds no parameter-level detail beyond restating the restrictions/thresholds concepts. It neither compensates for gaps nor harms understanding.

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 opens with a specific verb+resource pairing — 'Rule one food subject against the household premise' — which precisely scopes the operation to a single food item versus restrictions/thresholds. This clearly distinguishes it from siblings: check_plan (plan-level) and check_venue (venue-level).

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?

The description establishes clear context for when to call this tool ('one food subject') and routes the agent to register for API key creation. It doesn't explicitly name alternatives like check_plan as the 'when-not-to-use' path, but the singleton scope makes the boundary reasonably inferable.

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