Modify an image preset

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

Annotations already declare readOnlyHint=false, destructiveHint=false, so the mutation nature is known. The description adds crucial behavioral context beyond annotations: the null-to-clear semantics and the failure condition when the preset is missing. It does not contradict annotations. While it doesn't mention permissions or side effects, given the annotations, this is a solid disclosure.

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 sentences with no filler. The core purpose and differentiation are front-loaded in the first sentence, followed by the null-clearing and failure notes in the second. Every word earns its place, and the structure is scannable for an agent.

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?

With 8 parameters, all documented in the schema, the description covers the essential decision-making: when to use, null behavior, and failure mode. It doesn't mention the return value, but since there is no output schema, that might be expected. Still, the description is complete enough for correct invocation; a slightly richer mention of what happens after success (e.g., in-memory or persisted) would push it to 5.

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 each parameter is documented in the schema. The description adds a global semantic: 'Pass null for a field to clear it' and 'leave the rest alone', which clarifies the behavior of omitted and null fields—valuable beyond what the schema individually states. This elevates it above the baseline for high-coverage schemas.

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 verb ('Change'), the resource ('existing preset'), and the scoping ('some fields... leave the rest alone'). It explicitly differentiates from the sibling codex_preset_set by naming it and describing the exact condition for choosing this tool over it. No ambiguity remains about what this tool does.

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 gives explicit when-to-use guidance: 'Use this rather than codex_preset_set when adjusting one thing', and explains the rationale ('restating a long subject just to tweak a style is how a subject drifts'). It also warns about a failure condition ('Fails if the preset does not exist') and clarifies that omitted fields remain unchanged. This fully directs an agent on when to invoke this tool vs alternatives.

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