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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is known. The description adds valuable context: it reveals the output contains year-over-year CPI percentages (via the example), highlights data divergence patterns (medical care and housing vs headline), and states the data source (BLS CPI). This goes beyond what annotations provide, though it does not specify pagination or return format.

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 a single paragraph of four sentences. It front-loads the use cases and then provides a concrete example and source. Every sentence carries useful information, but it is longer than strictly necessary for a simple one-parameter tool, with some redundancy in the use-case list.

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 simple, one-parameter, read-only tool with no output schema, the description is quite complete: it gives use cases, an illustrative example of the output, and the data source. It does not explicitly describe the return structure (e.g., a percentage value for the selected category), but the example strongly implies it. Overall, the context is sufficient for basic usage.

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?

The schema has one parameter (category) with an enum but no description coverage (0%). The description references 'spending category' and gives examples for medical care and housing, which hints at the category parameter. However, it does not explain the available enum values or the default (all_items), and the mapping between the parameter and the returned component is only implicit. The enum names are self-explanatory, so moderate compensation, but it could be more explicit.

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 tool's purpose is implied through its name and description: it provides BLS inflation data by spending category. The description mentions 'analyzing inflation exposure by spending category' and uses examples like 'Medical care CPI +3.8% YoY vs headline CPI +3.1%', which clearly point to category-level CPI components. However, it never states a direct verb+resource definition (e.g., 'Gets inflation components for a given category'), and sibling tools like get_inflation_benchmark are not explicitly differentiated.

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 explicitly lists several use cases: analyzing inflation exposure, structuring vendor contract escalation clauses, benchmarking healthcare/real estate cost inflation, and monetary policy briefs. This gives clear context for when to use the tool. However, it does not mention when not to use it or suggest alternative tools such as get_inflation_benchmark, so it stops short of the full 'when/when-not/alternatives' guidance.

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