Ferry authoring guide

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

readOnlyHint=true already establishes the safety profile, so the description only needs to add context, which it does via the "read once" cue implying idempotent, cheap, cacheable content. It stops short of saying the output is prose documentation, but the gaps are minor given the annotation.

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, zero filler, and the content inventory is front-loaded before the usage instruction. Every clause earns its place.

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, read-only reference tool this is essentially complete: what it contains, when to read it, and that it is safe. Only a hint about the return being prose/markdown is absent, which is a negligible omission here.

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, so there is nothing for the description to disambiguate — the 0-param baseline applies. No syntax or format detail is required for an argument-free call.

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?

"Slide types, JSON shapes, and storytelling rules for explaining code changes" names the exact content the tool delivers and is unmistakably distinct from the deck-manipulation siblings like create_deck and add_slides. The agent knows immediately this is reference material, not an action.

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?

"Read once before building a deck" gives an explicit trigger and even a frequency constraint, telling the agent both when to call it and when not to call it again. No alternatives are needed since no sibling provides this documentation.

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