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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial context beyond them: paid-call cost caps ("at most 24 paid Jev calls... three otherwise"), latency budgets (55s vs five minutes), rate limits with Retry-After handling, prerequisite env vars, and which data goes to TypeSafe vs Jagex. It also warns that already-completed rounds may be billed and that there are no automatic paid retries — exactly the behavioral disclosure a caller needs.

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 purpose and sibling-routing are front-loaded, and the bulleted sections (Routing, Account, Setup/privacy, Cost, Timing/errors, Freshness, Outcomes) are tight and scannable. It is long, but the density is warranted by a six-parameter, multi-mode planner with paid calls and privacy implications; little of it is 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?

An output schema exists, so return values need not be described, yet the description still explains the outcome states (needs_context, no_match, goal_met) and how to act on them. Combined with setup prerequisites, billing, timing, caching and privacy notes, an agent has everything needed to call this correctly.

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 100%, so a baseline 3 would be acceptable, but the description adds real value with a worked example that shows how goal, goalType, targetSkill, targetLevel and context interact, plus the defaulting behavior ("52 defaults to 55") and the routing override of unlock over goalType. These clarify cross-parameter precedence that is easy to misread in the schema alone.

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 opening sentence gives a specific verb ("Plan") and named outputs ("next RS3 activity, training milestone or unlock prerequisite"), and immediately distinguishes the tool from siblings by assigning progress/levels/quest-facts/reference lookups to get_player_quests, get_player_stats, get_wiki_entity_facts and search_wiki. An agent can tell this is a planner/composer, not a data fetcher, without opening the 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?

Explicit routing rules are given ("unlock overrides goalType, otherwise goalType overrides inference; targetSkill sets focus, not the planner"), a concrete example is supplied, and sibling tools are named with the condition that selects them. When-to-use and how-the-modes-interact are both spelled out rather than inferred.

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