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

With no annotations, the description carries the full behavioral burden and discloses key traits: quarterly CAMD publication, default window of the last 7 days of the latest published quarter, that later dates are unavailable, the per-facility summary default, and hourly unit records for small windows. It omits authentication, rate limits, error behavior, and rules for combining state and facility_id, but covers the main operational constraints well.

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?

The description is front-loaded with the core purpose and then layers coverage, output fields, temporal constraints, format behavior, and use cases without repetition or filler. Every sentence contributes actionable context for selecting and invoking the tool.

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?

Given the complex EPA data source, no annotations, and no output schema, the description is largely complete: it lists returned fields, explains temporal availability, and contrasts summary versus hourly formats. It leaves a gap around required parameters—schema declares none required, but the description implies at least state or facility_id is needed—and does not address error handling or rate limits.

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 100%, so the baseline is 3, but the description adds meaning beyond the schema: it explains the default temporal window, that format=hourly returns unit-hour records suitable for small windows, and that state produces a state-wide aggregate. It also points to the summary_by_facility output for finding facility_id values, which is useful context not in the schema.

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 and resource ('Get hourly unit-level emissions from EPA Clean Air Markets Division (CAMD) for a specific US power plant or state') and scopes the data source and reporting population. The specificity of the EPA CAMD source and plant/state-level actual reported data implicitly distinguishes it from generic computation siblings like calculate_emissions, even without naming them explicitly.

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 provides clear intended use cases: 'Use for plant-specific carbon accounting, state-level fossil emissions and "dirtiest plants in [state]" queries.' However, it does not name alternative sibling tools or state when not to use this tool, so it stops short of explicit when/when-not routing.

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