Display calibration contract

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

The description asserts 'Read-only, zero-auth, no external side effects', but readOnlyHint, idempotentHint, destructiveHint and openWorldHint already convey most of that, so the value added is limited to 'zero-auth' and the fact that a JSON contract is returned. It does not disclose contract contents, versioning, or edge-case behavior beyond the 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?

Two tight sentences, front-loaded with the trigger condition followed by the guarantees and return type. Slight redundancy with the annotations in the second sentence keeps it from being maximally efficient.

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 zero-parameter, no-output-schema, read-only contract tool, the description covers trigger, safety profile and return shape well enough to invoke correctly. Only the exact structure of the returned contract is left unspecified, which is acceptable given there is no output schema to rely on.

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?

The tool takes zero parameters and the schema is an empty closed object, so there is nothing for the description to disambiguate. The baseline of 4 applies; the description correctly signals this is a parameterless contract fetch.

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 resource (display-calibration contract) and the domains it covers (display, color, ICC/LUT, artifact refs, measurement gates), plus the verb-like outcome 'returns a JSON display-calibration contract'. It is clear what the tool yields, though it does not sharply differentiate itself from adjacent siblings like telos.proof.visual or telos.rendering.capabilities.

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 'Use when ...' clause does give a positive trigger condition across several domains. However, there is no when-not guidance and no alternative named among ~37 siblings, so an agent cannot tell what to pick instead of this when the condition is only partially met.

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