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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real value with the caveat that counts are unadjusted for company size or facility count, which prevents a common misinterpretation of the ranking; it does not describe return ordering or result limits.

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: the ranking behavior and source lead, and the caveat follows. No filler and nothing repeated from structured fields.

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 single-parameter ranking tool with no output schema, the description covers what is ranked, the metric, the default, and a key interpretation limit. It omits how many companies are returned and the sort direction, but nothing essential blocks a correct call.

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% and the schema lists the three accepted values, so the baseline is 3. The description goes slightly beyond by naming the default ('deaths'), which the schema does not state.

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 ('Ranks parent companies by harm') plus the data source (EPA Risk Management Program accident histories), which distinguishes it from chemical_accident_search at the entity level. It does not name the sibling explicitly, so an agent must infer the ranking-vs-search split.

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 implies usage (ranking parent companies by harm) and documents the sort options with a default, but gives no explicit when-to-use versus chemical_accident_search or when the ranking view is preferable to raw accident search. Guidance is inferred rather than stated.

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