Best upgrades for an imported character

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

Beyond the readOnlyHint, it discloses the evaluation method (each mod simulated on this character in Path of Building at a good roll for its level, counting damage, effective HP and weakest max hit), a guaranteed inclusion rule (missing resistances, chaos when it is the weak spot), the return shape (topUpgrades per slot plus a trade search per slot), and a runtime estimate of 5-20 seconds. That is unusually rich disclosure for a read-only analysis tool.

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?

Purpose is front-loaded in the first clause, and every subsequent sentence carries distinct information (evaluation method, guarantees, return values, defaults, latency). It is dense but a single block with some nested parentheticals that take a second read.

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 9-parameter tool with a nested goals object and no output schema, the description covers the return shape (topUpgrades plus per-slot trade search), the defaults chain, and latency. Remaining gaps are the undocumented tuning parameters (avoid, maxTests, league), which matter less than the analysis semantics it does explain.

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?

With only 33% schema description coverage across 9 parameters, the description compensates for some: it explains where characterId comes from, that terms/defence/objective default from the character's main skill and gear or from goals, and that goals come from build_intake. But avoid, league, maxTests, and slots receive no explanation beyond the schema, leaving several parameters semantically thin.

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 states a specific resource and computation: per gear slot, what current mods are worth and which mods would help most, evaluated in Path of Building. It clearly frames itself as a per-slot upgrade analyzer for an imported character. It does not explicitly contrast itself with siblings like optimize_build or evaluate_build, so an agent must infer the boundary.

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 names the prerequisite explicitly (characterId from import_character) and explains defaulting behavior (terms/defence/objective from main skill and gear, or from goals), which tells the agent how to call it minimally. It gives no when-not-to-use guidance or explicit alternative routing against the optimization/evaluation siblings.

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