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

With no annotations, the description carries the full burden and does well: it discloses the response shape (Troutish plus English translation) and the non-obvious conditional behavior where the reply may contain a trout_asks field. It doesn't say whether conversation state persists between calls or whether the optional question can be ignored.

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, both load-bearing: the first establishes the actor and the return format, the second explains the conditional follow-up. Flavor is minimal and never crowds out the operational detail.

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 simple two-parameter tool with no output schema, the description covers what's needed: what to send, what comes back, and how to continue the exchange. Only persistence/statefulness and the undocumented `message` parameter are left implicit.

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 50%: `name` is documented, `message` is not, and the description only implies that `message` is what you 'say'. Nothing explains the 500/40 character limits, whether `name` is optional, or how your name affects the reply — so the description does not compensate for the coverage gap.

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?

'Say something to Old Gravel... rainbow trout of the OnlyFins pool' gives a concrete verb and resource plus the reply format, so the agent knows exactly what the call does. It doesn't distinguish itself from siblings like trout_dad_joke or trout_riddle, which are presumably also conversational prompts.

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 one follow-up path: 'Sometimes the trout asks an optional question (trout_asks) you may answer with answer_trout_question.' That names the alternative and the condition that selects it. It gives no guidance on when to prefer this over the other trout-themed siblings, though.

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