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

Annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) already carry the safety profile, so the bar is lower; the description adds genuine value by disclosing a per-call cost ('3 MESH/call') and a grounding trait ('Reasons from fundamentals; never invents patch notes or win rates'). This tells the agent the tool is faithful to provided data and costs resources to invoke. It does not say what external data it draws on, but the annotations cover the remaining safety burden.

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?

The description is compact at three sentences and front-loads the purpose before the behavioral caveats. The parenthetical '(3 MESH/call, a tool · gaming)' is minor noise that could live in metadata, but it does not meaningfully hurt readability or information density.

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?

This is a complex tool producing five distinct artifacts (counter-picks, bans, build, flex-slot rule, macro plan) with no output schema and a generic, misleading input schema. The description never clarifies how the agent should convey the enemy draft or rank, what the 'flex-slot decision rule' means, or what MESH cost implies for orchestration. An agent would struggle to construct a valid payload from this definition alone.

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?

Although schema description coverage is nominally 100%, the single 'input' parameter's description is a boilerplate copy from other tools — it gives agent-brain and agent-memory payload examples that say nothing about a draft-coach request. The tool description loosely implies the payload must contain the enemy draft, but no shape, fields, or format are specified for the nested object. This is worse than no parameter description because the provided text is actively misleading.

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 opens with a specific verb-plus-resource ('Read the enemy Mobile Legends draft') and enumerates concrete outputs: counter-picks, priority bans, a build with a flex-slot rule, and a first-5-minutes macro plan. It is scoped enough to be told apart from its nearest sibling, mobile-legends-value-coach, by the draft-phase focus. The 'Rank- and draft-order-aware' qualifier adds further precision.

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?

Usage context is implied rather than explicit: the draft focus and rank/draft-order awareness signal it is meant for the draft phase, but no sibling is named and there is no when-not-to-use guidance. An agent could reasonably wonder whether mobile-legends-value-coach covers post-draft or in-game decisions and when to choose one over the other. The description earns a baseline 'implied usage' score but no more.

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