adherence_summary

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds the specific scope (current plan) and time windows (7 and 28 days), which is useful context. It does not contradict annotations, and since the operation is read-only, no side effects need disclosure. However, it does not describe what happens if no plan exists or the interpretation of 'adherence,' but that is partially mitigated by the output 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?

The description is a single, focused sentence with no filler. The key information—time windows and scope—is front-loaded, making it easy for an agent to parse quickly. Every word contributes to meaning.

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 read-only tool with an output schema, the description is mostly adequate, but the missing parameter explanation leaves a gap. The tool depends on a 'current plan' concept that is not defined (likely from plan_get_current), and the description does not clarify this dependency. The output schema covers return values, so that is not an issue. Overall, it is minimally complete but could benefit from a brief note about the as_of parameter.

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 0%, and the description does not mention the 'as_of' parameter at all. The agent must infer that it specifies the reference date for metrics, and its nullability/default are only in the schema. Since the description should compensate for low schema coverage, this is a significant gap, though the parameter is optional and not critical to the core operation.

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 adherence metrics over 7- and 28-day windows for the current plan. It identifies the resource (adherence metrics) and the specific timeframes, making it distinct from sibling tools like log_adherence (which logs) and plan_get_current (which retrieves the plan). However, it lacks an explicit verb like 'retrieve' or 'get,' though the intent is unambiguous.

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 provides no guidance on when to use this tool versus alternatives. It does not mention that it is read-only (though annotations cover that) or contrast with log_adherence or plan_get_current. No conditions, exclusions, or prerequisites are stated, leaving the agent to infer usage from the tool name and description alone.

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