heropedia

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: the return format is raw markdown, matching is exact rather than pattern-based, and id is the preferred after-LIST path. Not a 5 because it doesn't say what happens on a miss or whether names are case-sensitive.

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 tight sentences: purpose first, then the two lookup modes in preference order, then a one-line exclusion. Every sentence carries decision-relevant information with no 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?

With no output schema, the description correctly tells the agent it will receive raw markdown, which is the key missing structured detail. It is otherwise complete for a two-mode lookup tool. Minor gap: no note on behavior when a lookup yields nothing.

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 0%, so the description carries the burden and does so: it explains that id and the hero_name/role_name pair are alternative lookup paths, that id is preferred, and that names must be exact. The oneOf exclusivity is enforced by the schema, and the description reinforces the intended usage rather than contradicting it.

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 (Retrieve) and resource (complete canonical Heropedia Role content) plus its format (raw markdown), which distinguishes it from the getList* siblings that only enumerate entries. An agent can tell immediately that this is the detail-fetch counterpart to the list tools.

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 explicit selection rules: prefer id after LIST, or use exact hero_name + role_name when both names are already known. It also excludes a misuse mode ('Not a regex tool'). It falls short of a 5 only because the sibling alternatives (getListByHero, getListByRole) are not named as the tools that produce those names.

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, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds genuine behavioral value beyond that by enumerating the returned fields (id, hero_name, role_name, description) and explicitly stating what is omitted (full Role prompts), setting return-size expectations.

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 short sentences, front-loaded with the action and the pagination mode, then the return contents and the exclusion. No filler, though the middle sentence is a plain field list that could be trimmed.

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 read-only, idempotent list tool with annotations covering safety and no output schema, the description adequately explains the return shape and the key exclusion. The main gap is pagination behavior, but the schema supplies defaults and bounds, so the definition is usable as-is.

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 0% for the two pagination parameters, so the description carries the burden of explaining them. It only says 'using pagination' and adds nothing about page defaults (1), the page_size maximum (100), or default (20). The agent gets no semantic help beyond the bare 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?

States a specific verb and resource (List Heropedia Hero/Role entries) plus the pagination mechanism. It also implicitly separates itself from getDetail by noting it does not return full Role prompts, though it never names its siblings getListByHero or getListByRole.

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?

Usage is implied by 'List ... using pagination' and the negative scoping hint ('Does not return full Role prompts'), which nudges the agent toward getDetail for full prompts. However, there is no explicit when-to-use or when-not-to-use guidance, and no mention of how getListByHero/getListByRole differ.

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 read-only, idempotent, non-destructive behavior, so the safety profile is covered. The description adds that the regex is case-insensitive and limited to a safe subset, plus a note about lightweight metadata, which is useful. However, it doesn't describe pagination behavior or rate limits, leaving some behavioral gaps.

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 tight sentences that front-load the core action and include only essential constraints. Every sentence adds value without redundancy.

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 the tool's simplicity (3 params, no output schema, rich annotations), the description covers the essential purpose and regex behavior. It could mention pagination defaults or how to use page/page_size, but overall it is sufficient for an agent to call the tool 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 description coverage is 0%, so the description must compensate. It explains the hero_regex parameter well (case-insensitive, safe subset) but provides no information about the page and page_size parameters, which are left entirely to the schema. Baseline 3 reflects partial compensation for the coverage gap.

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 verb+resource: it lists Hero/Role entries filtered by hero name regex. It is clear about what it returns, though it doesn't explicitly differentiate from sibling tools like getListByRole or getDetail beyond implying a name-based lookup.

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 clear context: 'Use when you know or can identify the Hero and want to inspect that Hero's available Roles.' This implicitly distinguishes it from role-based lookup (getListByRole) and detail (getDetail), but doesn't name alternatives or exclusion conditions.

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 readOnly/idempotent/non-destructive/non-openWorld, so the safety profile is covered. The description adds genuinely new context: the regex is case-insensitive, restricted to a 'safe subset', and results are 'lightweight metadata'. The safe-subset restriction is notable but never specified, and pagination behavior is unmentioned.

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?

Four short sentences, front-loaded with the operation and scope, then usage, then semantics. Slight redundancy between the first sentence and the 'Use when...' sentence, but no wasted verbiage.

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 no output schema, the description owes more on return values than 'Returns lightweight metadata'. Pagination guidance (page/page_size interaction with results) and result ordering are absent, leaving the agent with an incomplete picture of what a call yields.

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 0%, so the description carries the burden. It meaningfully enriches the key required parameter (case-insensitive regex, safe subset), but says nothing about page/page_size — those are only self-documenting via schema defaults and bounds. Partial compensation only.

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+resource ('List Heropedia Hero/Role entries') and constrains scope to entries whose Role name matches a regex, which implicitly separates it from getListByHero. It never names a sibling explicitly, so an agent must infer the distinction from the 'Role' filter alone.

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 clear when-to-use: 'Use when you want to inspect Heroes offering a particular Role.' No exclusions or named alternatives (getList, getListByHero) are given, so the routing decision is left partly to inference.

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