tibiawiki-mcp

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

The description goes beyond the readOnlyHint annotation by explaining the semantic meaning of the damage modifiers ('weak_to' means more than 100% damage, 'resistant_to' means less). This is critical for correct filter usage and is not derivable from the schema alone. It does not mention pagination or return format, but annotations already indicate a read-only, safe operation, and output schema exists.

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?

Two sentences with no filler. The first sentence states the purpose, the second immediately clarifies the most non-trivial semantic detail and provides an example. Information is front-loaded and every word earns its place.

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?

Given 13 parameters and an output schema, the description covers the essential tricky part (damage modifiers) and gives a usage example. It does not explain defaults for parameters like limit, sort, or include_inactive, but those are present in the schema. The exclusion of unrecorded hitpoints is documented in the schema for the relevant parameters. Overall, the description is sufficient for an agent to call the tool correctly, though it could explicitly mention that filters combine logically and that results are returned as a list.

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 description coverage is only 38%, leaving many parameters (sort, limit, cursor, is_boss, experience_min/max, etc.) undocumented in both schema and description. The description compensates for the damage-modifier parameters (weak_to, resistant_to) by explaining their meaning, but does not add value for the remaining parameters, which are fairly self-explanatory but still nominally under-documented. This partial compensation warrants a 3.

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 the verb ('Find') and the resource ('Tibia creatures') with a specific scope ('matching stat filters'). It distinguishes from siblings: tibia_get and tibia_search likely retrieve specific entities, tibia_find_items is for items, and tibia_how_to_obtain is a process. The tool's purpose is unambiguous.

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 provides a concrete example of when to use the tool ('which creatures are weak to fire and give over 500 experience'), which strongly implies typical usage scenarios. It does not explicitly mention alternatives or when not to use this tool, but the example is illustrative enough for an agent to recognize suitable queries.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering safety. The description adds behavioral nuance beyond annotations: the membership matching rule ('knight' matches 'knights') and the fact that filters are stat-based. No contradiction with annotations.

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?

Two sentences, front-loaded with the purpose and a clarifying example. Every clause earns its place, and the membership nuance is integrated naturally without bloat.

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 filter-based search tool with 13 optional parameters, an output schema, and read-only annotations, the description covers the primary use case and key behavior. It doesn't explain pagination (cursor/limit) or the include_inactive flag, but these are secondary to the core query pattern. Adequate for an agent to invoke it correctly in most scenarios.

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 description coverage is only 31%, and the description mentions 'attack, defense, armor and required level' but doesn't explain the min/max variants or that these are range filters. The example implies required_level_max, but many parameters (sort, limit, cursor, include_inactive) are left unexplained. It adds some meaning beyond the schema but does not fully compensate for the low coverage.

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?

States a specific verb ('Find'), resource ('Tibia items'), and scope ('matching class, type and stat filters'). The example query clarifies the exact kind of question it answers, distinguishing it from sibling tools like tibia_search (likely broader) and tibia_find_creatures (creatures, not items).

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?

Gives a concrete use case ('which two-handed swords need level 100 or less') and a membership nuance for vocation/weapon type. It doesn't explicitly state when not to use it or contrast with alternatives, but the example strongly implies the appropriate context.

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

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

Annotations already declare readOnlyHint=true, so the description wisely does not repeat that. It adds substantial non-obvious behavior: the full grammar of creature ability `area` grids, the meaning of effectTiles, and the caveat that effectOnCaster is wiki-stated rather than read from the grid. That is exactly the kind of context structured fields cannot convey.

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 and usage guidance are front-loaded, and the later area-grid passage is dense but not padded. Each clause adds a distinct semantic fact. It is longer than typical descriptions, but the length is justified by the genuinely complex output format it explains.

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?

With four parameters, 100% schema coverage, an output schema, and readOnly annotations, the description covers lookup semantics and the one deeply non-obvious output field. It does not describe missing-page behavior in prose, but that is not required given the output schema and the search-first instruction.

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 description coverage is 100%, so the baseline is 3. The prose adds meaning beyond the schema by explaining that `name` must be exact and that `type` resolves shared-name collisions. It does not add much for verbosity/include_inactive, but those are fully described in the schema.

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 names the operation ('Full detail') and the resource ('one named Tibia page') and enumerates every page kind, clearly distinguishing it from the search/find siblings. It even routes to tibia_search for uncertain names, so an agent can immediately tell what tibia_get is for.

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 explicitly says to use tibia_search first when the page name is uncertain and to pass `type` to disambiguate shared names. This gives concrete decision rules for the main usage choices without leaving them to inference.

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

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

Annotations already declare readOnlyHint=true, and the description adds no contradictory behavior. It adds useful context about the returned information (drop rates, NPC prices, quest rewards) without needing to restate the read-only nature. It does not cover rate limits or auth, but the simple read-only profile makes this adequate.

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?

Two sentences with zero filler: the first front-loads the core purpose and resource scope, the second gives the usage preference. Every word earns its place.

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 simple two-parameter tool with an output schema and read-only annotations, the description covers what it does and when to use it. The only minor gap is not explicitly explaining when include_inactive should be true, but the schema already documents it, so no critical information is missing.

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%, with both item_name and include_inactive described in the input schema. The description adds the single-item aggregation context but does not elaborate parameter behavior, so the baseline 3 is appropriate.

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 ('one item') and action ('Every in-game source ... in a single call'), enumerating creature drops, NPC sales, and quest rewards. This clearly differentiates it from siblings like tibia_find_items and tibia_find_creatures by emphasizing aggregation across source types.

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 gives explicit guidance: 'Prefer this over three separate lookups,' which tells the agent when to choose this tool instead of performing multiple queries. It does not name the specific alternatives or exclusion conditions, but the context is clear enough for selection.

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

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

Annotations already declare readOnlyHint=true, lowering the safety-disclosure burden. The description adds genuinely useful behavior beyond the schema: substring semantics, all-fourteen-types scope, and the shortest-name-first ordering with the rationale that 'the closest match leads.' It does not disclose pagination behavior, though the cursor parameter's schema description partially covers that.

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?

Three sentences with the purpose front-loaded, and each sentence earns its place: purpose/scope, the tibia_get relationship, and ordering behavior. The enumeration of all fourteen page types in the first sentence is somewhat redundant with the schema's types enum, so it is not maximally concise, but there is no wasted or filler content.

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?

Because an output schema exists and readOnlyHint is annotated, the description does not need to explain return values or safety. It covers the operational facts an agent needs — substring semantics, scope, ordering, and the tibia_get contract — while the schema covers the cursor mechanism. The only meaningful gap is guidance on when the specialized finder siblings should be preferred.

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 description coverage is 80%, so the schema already documents query, types, cursor, and include_inactive, and the description partly restates the fourteen-type scope that the types enum already lists. The ordering statement adds slight interpretive value for how limit selects results, but it does not add meaningful new parameter meaning beyond what the schema provides.

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 clause states a specific verb ('Find'), resource ('Tibia pages'), and matching mechanism (substring), then enumerates all fourteen page types to establish full scope at a glance. It also explicitly distinguishes itself from its siblings by framing the tool as the step that 'Turns an approximate name into the exact page name tibia_get expects.'

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 tibia_get linkage provides clear context: use this when you have an approximate name that must be resolved before calling tibia_get. However, it gives no exclusions and does not contrast itself with the specialized tibia_find_creatures and tibia_find_items siblings, so routing between the general and specialized finders is left to inference.

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