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

Annotations already declare read-only, idempotent, and non-destructive behavior, so the baseline is satisfied. The description adds valuable behavioral context by explaining what metrics are computed (value vs. cost, trend, success rate, pre-AI baseline) and that it is an analysis rather than a mutation. It does not contradict annotations.

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 two sentences, front-loaded with the primary purpose ('Calculate ROI per AI agent') followed by a concise breakdown of what it shows. Every phrase earns its place, with zero filler or repetition of schema details.

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 tool's moderate complexity (3 optional parameters, no required ones, read-only analytics), the description covers the essential behavioral overview and answers. The output schema exists and annotations are rich, so the description does not need to explain return formats or safety. It could mention how to filter by agent more explicitly, but the schema covers that.

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 parameters are already well-documented (days, workspace, agent_name). The description adds a small amount of context (e.g., 'per agent' and the baseline comparison) but does not meaningfully enrich the parameter semantics beyond what schema provides. Baseline of 3 is appropriate.

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 starts with a specific verb+resource: 'Calculate ROI per AI agent.' It clearly distinguishes itself from sibling tools by focusing specifically on per-agent ROI, not broader metrics like business impact or savings. It also specifies what it shows (value vs cost, trend, success rate, baseline), leaving no ambiguity about its purpose.

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 by stating the questions it answers: 'Is this agent generating or consuming value?' and 'What's the ROI trend?' This gives clear context for when a user would invoke it. However, it does not explicitly name alternative tools or state when NOT to use it, which would improve the score.

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