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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false. The description adds valuable context: it is 'free — no compute cost,' resolves any session_id to the root, and behavior after close_session_tree (authoritative credits). This adds meaning beyond annotations without contradiction.

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 dense with information but well-structured. It opens with a concise summary, then details the parameter, output, use cases, and constraints. While it could be slightly more concise (e.g., some redundancy in explaining the parameter), it effectively front-loads the key action.

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?

Despite having no output schema, the description thoroughly explains the return values (every session row with fields, cost events, self_cost_cents, total raw compute, tier markup, credits). It also covers org-scoping, free cost, and the condition for authoritative credits. Given the complexity of a fleet tree, this is complete.

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 single parameter, root_session_id, is described in the schema with a detailed explanation. The tool description adds further clarification that any session_id in the tree can be provided and that the handler resolves to the root. This goes beyond the schema's description, adding significant meaning.

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 clearly states it is a 'Read-only walk of a fleet session tree' that returns a full cost breakdown. It specifies the exact data returned (depth, parent, agent_kind, node_label, cost_events, self_cost_cents, etc.) and its scope (org-scoped). This purpose distinguishes it from sibling tools like fleet_analytics_overview which likely provide different analytics.

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?

The description lists explicit use cases: 'render cost breakdown UIs, audit fleet spend, or verify a session's tree topology.' It also notes org-scoping and that any session_id in the tree is accepted. While it does not explicitly say when not to use it or mention alternatives, the use cases are clear and sufficient for an agent to decide applicability.

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