Skip to main content
Glama

wiki_rank

Rank the wiki's entities by a NUMERIC field and return the top (or bottom) N. Use this for ANY 'which has the most/least/highest/lowest X' question — never guess-and-confirm with wiki_search. Choose a kind, the field to rank 'by', order (desc = highest first, the default; asc = lowest first), an optional limit (default 5, max 25), an optional 'category' to scope to one tag (food/item/species only — e.g. category "seed"), and an optional numeric 'where' filter. Available fields by kind (a field that doesn't apply to a given entity — e.g. a tool stat on a non-tool — simply excludes it): • food: calories, carbs, fat, protein, shelf_life, stack, vitamins, weight • item (base + placed-object + tool + block facets): air_pollution, animal_damage, block_tier, calories_burn, damage, durability_burn, fertility, fuel, fuel_jps, grid_radius, hardness, harvest_yield, housing_value, interact_distance, is_fuel, is_mintable, is_road, is_weapon, labor_max, labor_min, link_radius, max_coins, max_durability, move_efficiency, pollution, power_generated, power_watts, repair_level, room_tier, room_volume, school_value, seats, size_x, size_y, size_z, stack, storage_slots, storage_weight, tool_tier, vehicle_speed, weight • recipe: craft_minutes, crafting_steps, ingredients, labor, products, skill_level, skill_max_level, xp • skill: max_level, tier • species (animals ∪ plants/trees): attacks_player, calorie_value, co2_per_day, health, ideal_temp_max, ideal_temp_min, is_predator, nocturnal, yield_min_total, yield_total Bool fields read as 1/0 (e.g. where { field: "is_predator", op: "=", value: 1 }). Example: { kind: "food", by: "calories", order: "desc", limit: 3 } → the 3 highest-calorie foods. Scoped example: { kind: "food", by: "shelf_life", order: "asc", category: "seed" } → the seeds that spoil fastest. Optional character/server PROFILE (skill_level/skills, talents, modules/module, server) re-ranks the profile-sensitive metrics — recipe labor/craft_minutes; tool damage/calories_burn/durability_burn; item harvest_yield/power_watts; species yield_total/yield_min_total (craft_minutes also honors server craftTime). All other fields are static facts and ignore the profile (the result carries a note). No profile = base ranking.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
byYesNumeric field to rank by (see this tool's description for the field names valid for each kind).
kindYesWhich entity set to rank.
limitNoHow many to return (default 5, max 25).
orderNodesc = highest first (default), asc = lowest first.
whereNoOptional single numeric filter applied before ranking/aggregating, e.g. { field: "weight", op: "<", value: 1000 }. The field must come from the same per-kind set as 'by'/'field'.
moduleNoA single module name/type, or a comma-separated list (alternative to modules[]).
serverNoModel a DIFFERENT server's difficulty (default = this server's real settings; omit for accurate answers). Fields: craftResource, craftTime, growth, garbageRatio, fuelEfficiency, foodVariety, foodTastiness, baseGain, minBalanced, maxBalanced. Only craft_minutes is server-sensitive for ranking.
skillsNoPer-skill levels: { "<skill FullName>": level }. Overrides skill_level for those skills.
modulesNoUpgrade-module names/types installed (multiple slots stack).
talentsNoTalent names/types to treat as learned (profile-sensitive metrics only).
categoryNoOptional: scope to ONE tag/category before ranking/aggregating, e.g. "seed", "vegetable", "gun". Only the tagged kinds (food / item / species) support this. Use the category's name from a wiki_search result; matching is case- and plural-insensitive.
skill_levelNoA single skill level applied to every governing skill (profile-sensitive metrics only).

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description fully bears the transparency burden. It discloses profile re-ranking with specific fields (recipe labor/craft_minutes, tool damage, etc.), notes that static fields ignore the profile and the result carries a note, explains bool fields read as 1/0, covers server modeling, and clarifies that non-applicable fields exclude entities. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but it is well-structured with bullet-pointed field lists, clear examples, and logical sections. It front-loads the core ranking behavior and then systematically details parameters. While verbose, the complexity of 12 parameters and per-kind field distinctions justifies the length; almost every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 12 parameters, nested objects, and no output schema, the description is remarkably complete. It covers all parameter nuances, per-kind field sets, profile sensitivity, examples, and edge cases (e.g., non-applicable fields excluded, bool handling). It even notes that the result carries a note when profile is ignored. Nothing an agent needs for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all 12 params, but the tool description adds substantial meaning beyond the schema. It enumerates valid numeric fields per kind, explains the 'where' filter with an example, clarifies 'category' case/plural insensitivity, distinguishes 'module' vs 'modules', and details profile parameters such as skills, talents, and server settings and their effect on ranking.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Rank'), resource ('wiki's entities'), and outcome ('top (or bottom) N') with numeric field 'by'. It explicitly contrasts with wiki_search ('never guess-and-confirm with wiki_search'), making the tool's intended use clear and distinct from its main sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use: 'Use this for ANY "which has the most/least/highest/lowest X" question' and provides a direct exclusion ('never guess-and-confirm with wiki_search'). It includes concrete examples, a scoped-category example, and details on profile use, though it does not explicitly mention other siblings like wiki_aggregate.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation3/5

Most tools have distinct purposes (fetch, wiki_get, wiki_rank, wiki_calc, etc.), but search and wiki_search are clearly duplicated full-text search tools, and fetch vs wiki_get could be confused initially. Descriptions help but the overlap is notable.

Naming Consistency2/5

Naming is inconsistent: 'fetch' and 'search' lack the 'wiki_' prefix used by others, and there is a mix of verb-based (get, rank, calc) and noun-based (bom, contract_basics) names. Having both 'search' and 'wiki_search' for the same functionality is a clear naming violation.

Tool Count4/5

10 tools is within the ideal 3-15 range for a wiki server, covering search, retrieval, analytics, and recipe calculations. However, one tool is essentially redundant (search vs wiki_search), making the count slightly padded.

Completeness4/5

The tool surface covers the core wiki workflow: search, fetch markdown, read structured facts, rank/aggregate numeric data, and compute recipe-related metrics (BOM, raw materials, exact calc). Minor gaps like listing all entities of a kind without ranking, but overall no dead ends.

Resources