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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, so safety is covered structurally. The description goes further by disclosing the actual returned payload shape in both modes, including that each flow step carries a slide id and an 'available' flag indicating library membership. It omits error behavior for an id of the wrong type or a missing id.

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?

Content is front-loaded on the primary return payload, with the deck-flow variant second, which matches expected call frequency. The opening fragment "One library slide:" is slightly elliptical and the sentences are long and comma-heavy, but every clause adds information rather than filler.

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 must describe return values itself, and it does so in detail for both modes. For a one-parameter read tool with full annotation coverage, an agent has everything needed to select and invoke it correctly, aside from error handling.

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 0% and the single parameter is just an untyped 'id' with a pattern, so the description carries the full burden — and it does, explaining that the id is polymorphic: a slide id (from find_references) yields a slide, while a deck id (from find_deck_flows) yields a flow. That dual-mode semantics is real value beyond the schema. It does not restate the allowed character pattern or format.

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 names the exact resource (a library slide) and enumerates the payload it returns: labels, component layout v3, design DNA with 40 largest region boxes, and the mockup image. It also covers the second mode — a deck id returns a deck flow with ordered steps. This is a specific verb+resource statement that is hard to confuse with find_references or get_playbook.

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 routes the agent: use an id from find_references for a slide, or a deck id from find_deck_flows to get a flow instead. It also gives a usage constraint ("Build your own slide from it; never copy it"). It stops short of stating when NOT to call it or naming any other alternative, so a 4 rather than a 5.

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