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

With no annotations, the description carries the full burden and does so thoroughly: per-item parse failures return inline, a malformed app_bundle id aborts the whole batch with 400, an over-budget batch is refused whole with 429 and charges only the first unit. It also discloses the rate-limit cost model and per-tier limits, which are exactly the operational facts an agent needs before calling.

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?

Front-loaded with purpose, then failure semantics, then cost — a logical order with no filler. The tier list is dense but each figure is decision-relevant, and the min(200, remaining + 1) formula is stated as a reusable rule rather than a per-case enumeration.

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 tool with no annotations and no output schema, the description covers the risky, non-obvious behavior (partial vs atomic failure, budget refusal, weighting scope) rather than restating schema. The gap is the response payload: it says failures come back inline but doesn't characterize the successful score result, which an agent must otherwise infer.

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 50%, so the description must compensate. It adds real meaning for `weights` ('re-weights every entity in the call', i.e. applies across the whole batch) and hints at entity-id structure via the malformed-domain / app_bundle failure examples. It still doesn't describe the required `entity_ids` format beyond the schema example, so it isn't fully compensatory.

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 ('Scores up to 200 entities in one round-trip') and immediately carves out the batch niche against the single-entity sibling by emphasizing the 200-entity, one-round-trip scope. An agent can distinguish it from sigil_score_entity 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?

Gives a clear use context — 'built for agents evaluating many supply sources during campaign setup' — which tells the agent when this tool is the right pick. It never names the single-entity alternative (sigil_score_entity) or states the when-not condition, so routing is inferred rather than explicit.

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