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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral facts beyond that: no model is invoked, results are instant and free, source pages accompany each excerpt, and no registration is required. It stops short of describing how many excerpts come back or how they are ranked.

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?

Front-loaded with the core action and return shape, then the routing rule. Mostly economical, though 'No model involved: instant and free' and 'No registration needed' are two separate pitches for the same non-LLM selling point and could be tightened.

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?

An output schema exists, so return values need no explanation, and annotations cover safety. For a simple two-parameter retrieval tool the remaining gap is meaningful: the max_chars control is never described, so an agent can call it but not call it well.

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 0%, so the description carries full burden for the two parameters, yet it never explains them. The notion of a 'question' implies the query parameter, but max_chars (default 4000) is entirely undocumented — an agent has no way to know it truncates results or how to tune it.

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 verb and resource: retrieval of official Decibel documentation excerpts nearest a question, returned with their source pages. The parenthetical domain list (APIs, SDK, accounts, orders, margin, funding, liquidations, fees, vaults) pins down scope, and the contrast with ask_decibel lets an agent distinguish the two without opening a schema.

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?

Explicitly routes: use this tool for instant, non-model excerpt retrieval and use ask_decibel for a reasoned answer with sources. That is a concrete when-to-use-this vs when-to-use-alternative rule, plus a note that no registration is needed, leaving little to infer.

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