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

No annotations exist, so the description carries the full burden and does so: it discloses the name-matching rule (exact then substring, unlike resolve_card's fuzzy matching), warns that unresolved lines are dropped from every stat and cause under-reporting, and scopes the legality check to Core Constructed only, excluding rotation/Infinity/Poorcana. These are exactly the behavioral caveats an agent needs to avoid misreporting results.

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 purpose and benefit, then format, then reports, then behavior. Every section is useful, though the description is long and dense; a small amount of the enumeration (e.g. the full list of reports) could be tightened.

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?

An output schema exists, so return values need not be explained, yet the description still previews the report contents. Combined with the input-format rules, matching caveats, and legality scope limits, an agent has everything required to invoke this correctly and interpret the results.

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, and it does: it defines the accepted input format in detail (one card per line, '4x' or '4 ' both valid, quantity optional defaulting to 1, '#' and '//' lines skipped as comments). This fully documents the single parameter beyond the bare string type 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?

States a specific verb+resource (analyze a raw deck list) and enumerates exactly what it returns: ink curve, composition, and Core Constructed legality. It explicitly contrasts itself with a collection CSV and with the fuzzy resolver, so an agent can distinguish it from lookup_card, resolve_card, and enrich_csv without opening schemas.

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 when-to-use ('a decklist you already have — hand-written, pasted from elsewhere, or build_deck's output') and names alternatives for adjacent needs: what_am_i_missing for ownership/cost, and search_cards or build_deck(rotation_safe=True) for rotation safety. Exclusions are stated, not 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?

No annotations are provided, so the description carries the full burden and does so thoroughly: fields checked, promos skipped and why, one live API call per unique card (latency cost), read-only nature ('does not write any changes back'), and a disclosed false-positive class for Subtypes formatting, plus the clean-CSV return behavior.

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 purpose and scope, then behavior, then usage. The false-positive paragraph and the 'does not write' note each earn their place, but the enumeration of checked fields plus the promos explanation is slightly verbose and could be tightened.

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?

Output schema exists, so return values needn't be documented, yet the description still conveys the report shape ('csv_value' → 'api_value', grouped by card, one-line summary when clean) and the scope of checks. For a single-param reporting tool, nothing an agent needs to invoke it correctly 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 description coverage is 0%, so the description must compensate; it specifies that csv_path is an absolute path to an *enriched* collection CSV, adding the precondition that the file must already be enriched (otherwise the audit is meaningless). That is meaningful beyond the bare 'string' schema, though format/syntax detail is minimal.

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 (audit) plus resource (an already-enriched Lorcana collection CSV) and an explicit negation of the closest sibling behavior ('a correctness check on data already in the CSV, not a re-enrichment'). An agent can distinguish this from enrich_csv without opening either 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?

Gives concrete triggers (after a new set releases, after manual CSV edits, when enrichment output looks suspicious), an explicit when-not ('not as a routine step after every enrich_csv call') with the reason (per-card live fetches add latency), and names the correct remediation path (re-run enrich_csv, not hand-edit).

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?

With no annotations, the description carries the full burden and discharges it: it discloses that shortfalls are reported honestly rather than padded, that pricing comes from tcgcsv.com (and only for the gap in 'ideal' vs all cards in 'market'), that the builder is a heuristic curve/keyword-value optimizer and not a combo/synergy engine, and that a disclaimer is attached to every result.

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 purpose followed by tightly grouped bullet lists per mode and per argument; every sentence is functional. It runs long on Coconut-specific rules, but that detail is necessary given how unusual that format's legality rules are.

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?

An output schema exists, so return-shape explanation isn't required, and the definition still covers edge cases an agent would otherwise guess at: shortfall reporting, the no-build listing call, pricing scope per mode, and rotation behaviour. Nothing material is missing for correct invocation.

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% with six bare defaulted parameters, so the description must compensate and does: per-format ink_color counts, rotation_safe being a no-op outside 'core', coconut_card's fuzzy-name matching and the ink requirement, and the omitted-both-args listing behaviour. These are exactly the semantics the schema lacks.

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?

Opens with a specific verb, resource, and scope: 'assemble a legal, curve-balanced ~60-card decklist for an ink pair and format'. The three modes are enumerated immediately, so an agent can differentiate build behaviour without opening the 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?

Rich when-to-use guidance: mode semantics (collection vs ideal vs market), that collection_csv is required for 'collection', optional for 'ideal', ignored for 'market', and that the 'coconut' call with no coconut_card just lists the 18 Coconuts. It never names a sibling alternative (e.g. analyze_deck or what_am_i_missing), so routing between tools 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?

With no annotations provided, the description carries the full behavioral burden and does so thoroughly: it discloses that the tool writes two new files next to the input and never modifies input_path, describes API sources and 24h disk caching, explains promo-card handling, reports fill rates and unmatched cards, and clarifies cache_path and refresh_prices semantics.

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 front-loaded with purpose and workflow, and most detail is justified by the tool's complexity. It is somewhat long and repeats the write-two-files behavior in two places, but the information remains organized and useful rather than padded.

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 complexity, the lack of annotations, and the 0% schema coverage, the description is complete enough for correct invocation. It covers inputs, side effects, dependency ordering, caching behavior, price refreshes, output filenames, and edge cases; the presence of an output schema means return-value details need not be expanded further.

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 schema has 0% description coverage, so the description must compensate, and it fully documents all three parameters. It gives the expected format for input_path, explains that cache_path only skips re-fetching names already present in a prior enriched CSV, and states exactly what refresh_prices overwrites and when to use 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?

The description states a precise verb-and-resource purpose: enriching a raw TCGPlayer Lorcana CSV export with full card data. It explicitly names the dependent sibling tools that require its output, so an agent can immediately distinguish it from other collection 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?

It explicitly says to run this on every fresh TCGPlayer export before doing anything else, and names the exact situations for optional parameters: use cache_path on re-export for speed, use refresh_prices only to refresh an existing enriched CSV's prices, and leave refresh_prices off for same-day fresh exports. It effectively covers when to use the tool and when not to enable specific behavior.

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?

No annotations are provided, so the description carries the full burden and does so richly: live duels.ink fetch, Poorcana being offline/CSV-derived, promo-row exclusion semantics (excluded, not illegal), skipped rows being a data-lag note rather than a legality verdict, and the hard dependency on enrich_csv output columns. This is exactly the behavioral context an agent needs.

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 output shape are front-loaded, and every subsequent sentence carries distinct information (offline exception, promo handling, skipped-row caveat, dependency, alternative tool). It is longer than typical and slightly dense, but there is 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?

Output schema exists, so return values need no explanation; the description instead covers inputs, offline/online behavior, edge-case row handling, upstream dependency, and the sibling alternative. Nothing needed to invoke it correctly 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 0%, so the description must compensate, and it largely does: csv_path is defined as an absolute path to an enriched Lorcana CSV (with a warning about raw exports), and the valid format values are enumerated in prose despite the schema lacking an enum. It omits that format defaults to 'core', which the schema only implies via a bare default value.

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 (filter), resource (enriched collection CSV), scope (cards you own legal in format X), and output shape (grouped by ink color with owned quantities). An agent can tell it apart from build_deck and enrich_csv without opening any 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?

Explicit when-to-use ('before hand-building a deck', 'sanity-check whether a deck idea is feasible') and an explicit when-not with the named alternative: use build_deck with mode="collection" instead, which already applies this filter internally. Nothing 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?

With no annotations, the description carries the full burden and does so: it explains the Singer-keyword eligibility rule, result grouping/ordering, fuzzy name resolution, the error path for zero-or-two arguments, the limit cap, and the explicit limitation that it does not evaluate stats or combo consistency unless collection_csv is passed.

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 purpose and the sibling contrast, and every sentence carries information. The parenthetical asides (Steelsong example, typo note) add length but also real value, so it is slightly verbose rather than padded.

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 lookup tool with an output schema already documenting return shape, the description supplies everything else an agent needs: eligibility logic, argument exclusivity, ordering, and the ownership caveat.

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%, so the description must compensate, and it largely does: it defines song_name (fuzzy), cost as a raw threshold, colors as comma-separated inks with an example, collection_csv's path/effect, and limit's default and 200 cap. Only the cost default sentinel (-1) is left unexplained.

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 ('Find every Character that can sing a given song') and immediately names the sibling it is not, routing general card search to `search_cards`. An agent can distinguish it from `search_cards`/`filter_collection` without opening any 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 frames the use case (building/checking a Singer/song combo) and the anti-case (general card search → `search_cards`). It also states the mutual-exclusion rule: exactly one of song_name or cost, with an error otherwise.

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?

With no annotations, the description carries full burden and does so exceptionally: it discloses that this is NOT a live fetch, that data is a versioned package snapshot, that the response self-reports snapshot date/sources, that rows are flagged verified vs. unverified, and that decklists are best-effort transcriptions. These are exactly the caveats an agent needs to avoid over-trusting the output.

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 purpose and mode split, and every sentence adds real information (data provenance, verification flags, transcription caveats). It is on the long side and slightly repetitive about the non-live-fetch point, but no sentence is 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?

Despite an output schema existing, the description still communicates the shape of the alternate mode's return (standings + decklists) and the freshness caveats, and covers both filter parameters without gaps. Nothing an agent needs before calling 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 0%, so the description fully compensates: it documents `ink_colors` syntax (comma- or slash-separated, order-insensitive, ignored when `event` is set) and `event` as a key or name fragment with concrete examples, plus the mode switch each triggers.

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?

Opens with a specific verb+resource+scope: returns a Core Constructed metagame snapshot (tier list of two-ink pairs plus recent tournament results), and explicitly notes the alternate `event` mode returning standings and decklists. It also distinguishes itself from siblings by naming build_deck/analyze_deck as complementary rather than equivalent.

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?

Explicit when-to-use ('what's currently good', 'is my ink pair competitive', 'context before build_deck') and when to switch modes (pass `event` for a specific event's lists). Alternatives are named directly, so routing is unambiguous.

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?

With no annotations, the description carries the full burden and does so: live data sources (duels.ink for legality/images, tcgcsv.com for prices), 24h caching, graceful-degradation behavior ('shown as "?" / omitted (never errored)'), and the gameplay-relevant fact that Enchanted/Epic printings differ only in number/rarity/price. This is behavior an agent cannot infer from the schema.

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 core purpose and routing are front-loaded in the first two paragraphs, which is ideal. However, the trailing 'Args:' block restates the `fmt` details and `name` semantics already given in prose, adding some redundancy to an already long description for a two-parameter tool.

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?

An output schema exists, so return values need not be explained, and the description covers everything else an agent needs: matching behavior, format handling, data provenance, and failure modes. Nothing essential is missing for correct invocation.

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%, so the description must compensate and it does: the `fmt` enum values are enumerated (core, infinity, core_ja, core_zh, poorcana, coconut) along with its effect (adds a legality column, sorts legal cards first), and `name` matching is spelled out as an ordered resolution chain, including how a bare character name differs from a full name.

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 a specific verb+resource ('List every printed version of a Lorcana card') and the scope (all printings side by side), then explicitly distinguishes itself from the sibling: 'lookup_card silently collapses to just the newest printing; this shows them all.' An agent can route between the two without opening either 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?

It states the exact selection condition ('Reach for this whenever the answer depends on which printing') and reinforces it with four representative questions, plus the explicit alternative (lookup_card) and why it is wrong for these cases. Nothing 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?

With no annotations, the description carries the full burden and does so richly: exact-then-substring matching (not fuzzy), silent selection of the most recent printing when multiple exist without set_name, the consequence for older printings' IDs/legality, and live fetch with 24h disk caching plus cache-invalidation guidance. These are precisely the non-obvious behaviors an agent needs.

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 lookup purpose, then behavior, then usage routing. It is long, but nearly every sentence carries actionable detail (fallback matching, silent recency, caching); only mild tightening is possible without losing signal.

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?

An output schema exists, so return-value explanation is unnecessary, and the description still summarizes the payload (stats, abilities, legality). For a two-param lookup with no annotations, the behavioral, usage, and parameter context is complete enough to call it 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 coverage is 0%, so the description must compensate, and it largely does: concrete examples for name ('Mirage - Super Recruiter' or just 'Mirage') and set_name ('Wilds Unknown'), plus the behavioral effect of omitting set_name. It doesn't explicitly note whether set_name must be an exact string or how mismatches behave, leaving a minor 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 (look up), resource (one already-known Lorcana card), and the scope of the return (full stats, abilities, format legality) in one call. It clearly distinguishes itself from resolve_card (fuzzy) and search_cards (browsing), so an agent can route without opening siblings.

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 names when to use this (specific printed card name, even with subtitle omitted), the exact failure condition under which to switch (a 'no card found' result for uncertain/informal/misspelled names), and the correct alternative in each case (resolve_card for fuzzy disambiguation, search_cards for browsing). Nothing 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?

With no annotations, the description carries the full burden of behavioral disclosure. It reveals the tool's tolerance for typos, missing dashes, missing subtitles, and word order, and details the three possible return shapes (single match, top-3 list, no match). This gives the agent a complete understanding of what to expect.

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 well-structured and efficient: a one-sentence summary, a brief behavior paragraph, a list of return shapes, and an Args block. Every sentence earns its place, and the format is easy for an agent to parse.

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 output schema exists, the description covers all necessary context: the tool's purpose, its behavior, when to use it (vs. lookup_card), and the possible outcomes including the no-match scenario. It is comprehensive for a fuzzy-matching lookup 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?

The schema provides no parameter descriptions (0% coverage), but the description compensates fully. The Args section explains that `name` accepts informal, partial, or misspelled names, and `set_name` is an optional narrow with an example ('Wilds Unknown'). This adds significant meaning 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 clearly states the tool's purpose with a specific verb ('Resolve') and resource ('informal, misspelled, or subtitle-less card name to specific card(s)'). It explicitly distinguishes this tool from lookup_card by contrasting its tokenization and scoring approach with substring matching.

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 provides direct usage guidance: 'Use this when lookup_card fails or when you're not sure of a card's exact printed name.' This explicitly states when to use this tool and names the alternative (lookup_card), making the selection criteria clear.

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?

With no annotations, the description carries the full burden and does so: it discloses the live cached LorcanaJSON source (never a local CSV), that newest sets are always included, that stat-less card types render '—' rather than being dropped, the group-by-color output shape, and that pagination returns the exact next offset. These are behavioral traits an agent could not derive from the schema.

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 are front-loaded and the Args block is tight and scannable, but there is mild redundancy (ownership/price independence is stated twice, and the format-legality sentence is convoluted). Slightly longer than it needs to be, though no section is wasted.

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 an 11-parameter optional-filter tool, this covers filtering semantics, defaults, pagination, data freshness, and edge-case rendering. An output schema exists, yet the description still usefully notes the Markdown-table/color-grouping return shape and no-price/no-ownership content, which is relevant to how the agent must post-process results.

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, and it does for all 11 parameters: it defines AND semantics for filters, documents the ANY-of behavior for colors (dual-ink cards included), enumerates valid card_type and rarity values, explains the -1 sentinel for cost bounds, and gives examples for keyword, subtype, and set_name substring matching.

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?

Opens with a specific verb+resource (search the full Lorcana card pool) and immediately scopes it with a negation ('not your collection'), which is exactly the distinction that separates it from filter_collection and what_am_i_missing. An agent can classify this tool without opening 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?

Names concrete alternatives and the conditions that select them: resolve_card/lookup_card for a single known (even misspelled) name, what_am_i_missing or find_song_synergies for ownership, filter_collection for format legality. Also states that no filters returns the whole pool, so the boundary case is explicit rather than inferred.

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?

No annotations are provided, so the description carries the full behavioral burden, and it does so richly. It discloses name-matching rules (exact-then-substring, not fuzzy), unresolved-name handling, output sections, pricing source order (CSV TCG Market Price first, tcgcsv.com fallback only for zero-owned cards), 24h caching, and that the total is a snapshot rather than a quote.

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-loads purpose and remains well structured with clear usage guidelines and args sections. Some pricing and matching details are verbose, but most sentences earn their place given the tool's complexity; a small amount could be trimmed without losing correctness.

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 no annotations, low schema description coverage, and an existing output schema, the definition supplies all context an agent needs: scope, alternatives, matching behavior, failure handling, pricing logic, and usage sequence. Return values are covered by the output schema, so the description need not explain them further.

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, and it does for both required parameters: deck_list format and example, and collection_csv as an absolute path to an enriched CSV. It stops short of enumerating expected CSV columns, but for a 2-param tool with a sibling enrich_csv, the description adds meaningful semantics 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 comparison: deck list vs. collection, returning owned/missing/short cards and estimated completion cost. It explicitly distinguishes itself from analyze_deck (curve/legality) and build_deck(mode="ideal") (deck construction), so an agent can select it correctly without opening sibling schemas.

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 exact when-to-use criteria: after obtaining a specific decklist and before playtesting/buying. It names alternatives and the conditions that select them: analyze_deck for legality/curve, build_deck(mode="ideal") when building around collection constraints, and lookup_card/resolve_card for matching behavior.

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