match_calibration

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

Annotations already mark it as read-only and non-destructive, so the bar is lower. The description adds useful behavior beyond that: it returns reasoning, warnings, blocking issues, and mandates showing the plan to the user. It clarifies algorithmic behavior and output properties without contradicting the readOnlyHint.

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 information-dense but well-organized, with the core purpose first, the matching criteria explicit, and the return/workflow behavior listed compactly. Each sentence adds needed value, even the policy and warning 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?

There is no output schema, so the description carries the burden of explaining return information, and it does so at a reasonable level by naming reasoning, warnings, and blocking issues. It is complete enough to guide correct invocation, though the exact structure of returned policy/warnings is left to runtime discovery.

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 coverage is only 33%, so the description must compensate for the otherwise undocumented light_group_id and allow_dark_scaling. It partially does so by explaining the calibration policy and when dark scaling applies, but it adds little explicit meaning for the force parameter and no direct explanation of light_group_id beyond the general statement.

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 uses specific verbs and resources: it chooses darks/flats/flat-darks/bias for a light group and outputs a CMOS calibration policy. It clearly distinguishes this from calibrate_lights and list_masters by explaining the matching rules and planning role.

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?

It explicitly scopes the tool to 'a light group from the last scan' and instructs to 'show the plan to the user before stacking', providing clear workflow context. It does not name alternative tools or say when not to use it, but the context is strong enough for an agent to infer the intended call timing.

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