The Doll Scout · Collecting Tools

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes beyond them by disclosing the modeling assumptions (equally likely regular styles, replacement by a secret) and explicitly disclaiming that results are 'not official series odds or sealed-case allocation'. This is exactly the kind of context annotations cannot carry.

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?

Front-loaded with the core purpose, then the mode requirements, then the caveat — a sensible ordering. Slightly dense and acronym-heavy ('secretOddsN'), but every sentence carries information.

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 5-parameter tool with no output schema and no conditional logic in the schema, the description covers the mode/parameter contract and modeling assumptions well. It still leaves the return shape and the meaning of 'boxes' while omitting any distinction from the overlapping sibling tool.

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 it names three of the five parameters (regularStyles, secretOddsN, probabilityPercent) and explains their conditional dependency on the mode — semantics the flat schema cannot express. It does not explain 'boxes' or the 'target' enum values, leaving a small residual 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?

States a specific verb+resource ('Calculate independent-box chances') and scopes it to the three target modes (regular style, secret, printed). However, it never distinguishes itself from the very similar sibling secret_pull_probability, leaving the agent to guess which probability tool to call.

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 'Required by mode' sentence gives concrete per-mode parameter requirements, which is useful routing guidance. But there is no explicit when-to-use vs. when-not-to-use and no mention of the sibling secret_pull_probability that appears to overlap; usage is only implied.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real value: it discloses the return contents (success/failure chances, max and expected spend), the stopping rule (first target), the single-currency assumption, and cent rounding.

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 dense sentences with no filler, and the core comparison is front-loaded before the return/constraint details. Efficient, though the second sentence packs return values, currency rules and exclusions into one long clause.

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 usefully names what is returned, and annotations cover the safety profile. But for a five-required-parameter tool at 0% schema coverage, the failure to define fixedCost and probabilityPercent leaves a meaningful gap an agent would need filled before calling it.

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?

Five parameters at 0% schema description coverage, so the description carries the full burden. It hints at budget, confirmedCost ('confirmed-figure quote') and cents rounding, but fixedCost is never addressed and probabilityPercent is only vaguely suggested by 'chances'; boxCost is implied at best. The mapping stays loose.

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 (compare) and two clearly defined operands: a capped independent blind-box budget and a user-supplied all-in confirmed-figure quote. This is distinguishable from probability-focused siblings, though it never names an alternative to remove ambiguity.

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 closing clause excludes two scope-adjacent uses ('not a purchase recommendation or price lookup'), which implies it is a pure decision-math tool. However, it gives no guidance on when to prefer this over siblings like secret_pull_probability or estimate_collection_progress, leaving the selection 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, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: alias matching and the fallback that an unknown term returns the list of available terms, which tells the agent how to recover from a miss.

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?

It is a single front-loaded sentence that leads with the action and resource. The long parenthetical enumeration is dense but earns its place by delimiting scope.

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 one-parameter lookup with no output schema, the description covers scope, alias behavior and the unknown-term fallback, which is enough for correct invocation. Return-format details are not required since the lookup is a simple definition.

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% and the single 'term' parameter already documents its purpose with examples ('lafufu', 'printed odds'). The description adds only the vocabulary list, which overlaps with the schema examples, 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 names a specific verb (define) and resource (a Labubu/blind-box collecting term) and enumerates the covered vocabulary, so the agent knows exactly what this tool answers. It is clearly distinct from siblings that compute odds or display plans.

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 implicitly scopes usage to looking up the meaning of a collecting term and notes alias matching, giving the agent a clear context for invoking it. It does not explicitly contrast itself with get_collecting_guide or the other sibling tools, so no exclusion guidance is provided.

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 cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral context by disclosing the statistical assumption (equally likely regular styles after combined secret probability removed) and the definition of 'owned' – important caveats for interpreting an estimation.

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 core function before the assumption and exclusions. Each sentence adds a distinct constraint (function, assumption, term definition, exclusion) with little waste.

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?

No output schema exists, yet the description never explains what the estimate returns (predicted counts, probabilities, expected new styles) or how to interpret it. Combined with 0% parameter coverage, it leaves enough gaps that an agent cannot fully predict the response.

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 0% across four required parameters, so the description must carry the load. It partially does: 'Owned means distinct regular styles from this exact series' maps to ownedStyles, and 'independent boxes' / 'combined secret probability' gesture at boxes and secretPercent, but no units or exact mappings are given for regularStyles or secretPercent.

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 (estimate) and resource (collection progress: distinct regular styles, repeated draws, secret draws), so the function is clear. The closing 'Not sealed-case allocation or completion probability' helps separate it from siblings like compare_blind_box_budget, though it doesn't name them directly.

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 meaningful exclusion ('Not sealed-case allocation or completion probability') and states the modeling assumption, which implies when it applies. But it never names which sibling to use instead (e.g., secret_pull_probability, calculate_style_probability), so routing 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.

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 still adds meaningful behavioral context: what is returned (canonical links, supported languages, inputs, callable functions) and a concrete negative constraint that browser-only collection records are never read.

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 with no filler; the core action is front-loaded and the return contents and constraint follow. Nothing is wasted, though the return-list sentence could be slightly more compact.

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 usefully enumerates what comes back and flags the browser-only exclusion, which is the key completeness concern for a discovery tool. The remaining gap is that task enum values are never explained in either the schema or the description.

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 50% — the 'language' enum is documented but the 'task' enum values are not described anywhere. The description mentions 'by task' and 'supported languages', but adds no detail on what each task category or language code means, so it does not compensate for the 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 and resource ('Find TDS collecting tools and guides') scoped by 'task', which clearly separates it from content-retrieval siblings like get_collecting_guide. It does not name any sibling explicitly, but the discovery/index framing 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?

'by task' implies when to use it (you have a task category in mind) and the exclusion 'Browser-only collection records are never read' hints at scope limits. However, there is no explicit statement of when to prefer this over get_collecting_guide or the other lookup siblings.

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 and closed-world, so safety is covered. The description adds real value beyond them by disclosing what comes back (source links, review date, limitations), which explains the guide's trust profile and recency characteristics.

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, zero filler. The positive capability is front-loaded and the exclusion clause follows immediately where an agent's decision ambiguity would sit.

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?

No output schema exists, but the description compensates by naming the return contents and their caveats, and the annotations cover the safety profile. Adequate for a 2-parameter read tool, though it says nothing about guide length, depth or language coverage per brand.

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 50%: the language parameter is documented in-schema, but the brand enum carries no per-value description. The description only states there are eight brands, which the enum already establishes, so it adds no meaning about brand-specific content differences. 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?

Specific verb (Read) plus resource (published guide) and scope (one of eight collectible brands), with the payload spelled out: official source links, review date, limitations. The final exclusion sentence separates it from sibling tools like labubu_fake_signals and labubu_rarity_odds without needing to open a 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?

Explicitly states when NOT to use it (current stock, resale valuation, authentication), which rules out the closest sibling intents. It stops short of naming the correct alternative tool for those cases, so routing is implied rather than prescribed.

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 establish it as read-only, idempotent, non-destructive, and closed-world. The description adds value by disclosing that the signals are compiled, not a guarantee, that limitations are included, and that each check has named public sources—provenance and reliability context not captured by 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 core content and followed by a concise caveat. The parenthetical list of eight checks is dense but earns its place by specifying exactly what the tool returns.

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 no-input read-only resource with rich annotations and no output schema, the description covers the core content (eight checks, sources, limitations). It could specify the return format or that it is static, but given the lack of an output schema, it is nearly complete.

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?

The tool takes zero parameters, so there are no parameter semantics to document. Per the baseline, a 0-param tool earns 4; the empty schema with additionalProperties false is self-evident and needs no description.

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?

Names the specific resource (eight authenticity checks for a Labubu figure) and enumerates them, making it distinguishable from siblings like style probability or rarity odds. However, it uses a noun phrase rather than an action verb (e.g., 'Get...'), so it is slightly less direct than a 5.

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?

Provides no explicit when-to-use, when-not-to-use, or sibling alternative. The caveat 'not a guarantee' is a limitation, not guidance for selecting this tool over define_labubu_term or get_collecting_guide.

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 behavior, so the safety profile is covered. The description adds real behavioral context beyond that: the data is 'commonly reported' (not authoritative), each row carries a source, and the response self-documents the box-printed-odds hierarchy. It stops short of noting data freshness or coverage limits.

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, densely front-loaded with the verb, resource, and breakdown, followed by the ranking caveat. No filler, though the second sentence's phrasing ('and the result says so') is slightly indirect for the value it carries.

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 parameters, no output schema, and no nested objects, the burden of describing the return falls on the description, which does so adequately (per-row odds grouped by series format, each with a source, plus a precedence note). A brief note on coverage scope or how to resolve a specific series would make it fully complete.

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?

The tool takes no parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description appropriately spends its words on output semantics instead.

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 names a specific resource (commonly reported secret/chase odds for Labubu / The Monsters blind-box series) and the granularity (by series format: 6-figure, 12-figure, collabs, glow variants) plus provenance (per-row sources). It implicitly separates this lookup tool from the probabilistic siblings like secret_pull_probability, but never names an alternative, so it falls short of a 5.

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: consult this when you want reported/chase odds per series format. The caveat that box-printed odds outrank any returned row is useful prioritization guidance, but the description never states when to prefer this over sibling tools such as secret_pull_probability or calculate_style_probability.

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, and closed-world behavior. The description adds useful scope and behavior context: it tests 90-degree rotation when allowed, treats all dimensions as the same unit, and explicitly disclaims 3D packing and safety certification. It does not contradict annotations and enriches understanding of what the calculation does and does not do.

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 description is three sentences, front-loaded with the core purpose, and every sentence adds distinct value: scope, unit constraint, rotation behavior, and exclusions. There is no filler or 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?

With no output schema and low schema description coverage, the description should carry more burden. It omits any explanation of return values, layout output format, or parameter roles, leaving an agent without enough information to interpret results or fully understand inputs. Annotations cover safety aspects, but the description is not complete enough for this calculation tool.

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 13% (only 'gap' has a description). The description adds a helpful unit-consistency note ('All dimensions use the same unit') but does not map parameters to their roles (case vs item dimensions), explain the 'rotate' flag, or clarify any other parameter beyond what the intuitive names suggest. Given the low coverage, the description should compensate more than it does.

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 (calculate) and resource (uniform single-layer rectangular layout for toy footprints inside a display case), and explicitly rules out 3D packing and safety/load certification. This makes the tool's purpose unambiguous and distinguishes it from any generic packing tool, even though the listed siblings are unrelated.

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 implies when to use the tool (for single-layer rectangular display layouts) and gives a clear exclusion ('not 3D packing or a safety/load certification'), but it does not name alternatives or state a positive trigger condition. Usage is therefore inferred from the purpose statement rather than explicitly guided.

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, idempotentHint, and destructiveHint=false, so safety is covered. The description adds genuinely useful model semantics: the independent single-box assumption and the caveat that sealed whole-case allocation can produce different results. That is context beyond what annotations provide.

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, no filler, with the primary output (pull probability) front-loaded before the secondary outputs and caveat. The em-dash caveat is information-dense but 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?

There is no output schema, and the description compensates by naming the returns: the probability plus the 50% and 90% box counts. Combined with the model caveat, an agent has enough to invoke and interpret the tool correctly, though the sibling relationship remains unaddressed.

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% and both parameters carry examples ('e.g. 12', 'e.g. 72'), so the schema does the heavy lifting. The description repeats the 1-in-oddsN and N semantics without adding format or edge-case detail beyond 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 description states a precise computation: probability of at least one secret in N blind boxes at 1-in-oddsN odds, plus the box counts for 50% and 90% thresholds. That is specific verb+resource+scope. It never names the close sibling calculate_style_probability, so the agent must infer the distinction from the word 'secret' 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?

It gives a validity condition ('Independent single-box model — sealed whole-case allocation can differ') rather than when-to-use guidance. No explicit routing to or away from alternatives such as calculate_style_probability is provided, so usage is only implied.

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