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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description adds meaningful behavioral context: the operation also rolls out the change, and the tool rejects secret-looking keys. These are guardrails and side effects not visible in the schema.

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?

Three compact sentences deliver the action, the appropriate use case, and the alternative tool. No filler or redundancy; the most important guidance is front-loaded.

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 3-required-param tool with no output schema, nested objects, or enums, the description provides everything needed to select and call it correctly: what it does, when to use it, and when to choose a sibling. Nothing critical is missing.

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 schema already documents all three parameters. The description adds only illustrative examples (LOG_LEVEL, feature flag) without changing parameter meaning, so the baseline 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?

States a specific action: 'Set a single environment variable on an app and roll it out,' with concrete examples (LOG_LEVEL, feature flag). It clearly differentiates from set_app_secret by noting that secret-looking keys are rejected, so an agent can distinguish the tool from its sibling without opening schemas.

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?

Explicitly tells the agent when to call it ('when an app needs plain configuration') and when not to, directing it to set_app_secret for secrets. The contrast between plain configuration and secrets gives a clear decision rule.

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