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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context: the verdict is based only on supplied evidence and the tool does not inspect code/CI/deployment, which further clarifies its safe, read-only nature. This goes beyond what annotations provide.

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 core output (verdicts), then immediately clarifies scope. No unnecessary words. Every sentence adds value.

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?

The description explains the tool's purpose and limitations but does not explain how the verdict is determined (e.g., thresholds for GO/NO_GO) or detail all required inputs. With 12 required parameters and no output schema, more information about the decision logic would be beneficial.

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 low (38%). The description mentions 'acceptance-criterion results, check evidence, rollback, monitoring, limitations, and independent review' which maps to some parameters but does not detail each of the 13 parameters. It provides a high-level mapping but insufficient detail for an agent to understand all inputs.

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 one of three verdicts (GO, CONDITIONAL, NO_GO) based on supplied evidence, and explicitly distinguishes itself from tools that inspect code/CI/deployment. This differentiates it from sibling tools like search or fetch.

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 states the tool is for use when acceptance-criterion results, check evidence, rollback, monitoring, limitations, and independent review are available. It explicitly says what it does NOT do (inspect code, CI, deployment), providing clear when-not-to-use guidance. However, it does not mention alternative sibling tools for those cases.

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