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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds output details (medians, segments) and a source, but it introduces a significant transparency gap: it says 'software category spend' while the required parameter is vendor_name. This mismatch likely misleads the agent about what input to provide, which is a behavioral disclosure issue beyond what annotations offer.

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 coherent paragraph that front-loads the 'when to use' guidance, includes a concrete example with illustrative numbers, and names the data source. It is not overly verbose, though the example does take up space that could have been used to clarify the input.

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?

There is no output schema, so the description must fully define the contract. It provides return segments and an example, but it fails to explain the required vendor_name input and how it maps to a software category. This is a critical completeness gap for a tool with only one parameter—without that clarification, an agent cannot correctly invoke the tool.

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 description provides zero information about the vendor_name parameter and even suggests the input is a software category instead. With 0% schema description coverage, the description was expected to compensate, but it actively misdirects the agent about the required input, making this a critical failure.

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 clearly states the tool returns SMB, mid-market, and enterprise median monthly spend for software categories, positioning it as a size-segmented benchmarking tool. The verb 'returns' and the resource 'median monthly spend by company size' are specific and differentiate it from sibling tools that focus on other dimensions like industry or vendor.

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 spells out the intended use case: 'Use when benchmarking software category spend against same-size organizations before a purchase or renewal.' This gives clear context, but it does not mention exclusions or alternatives, such as when a different benchmark tool would be more appropriate.

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