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

With no annotations, the description must carry the full behavioral burden. It does disclose caching behavior ('refresh: bypass the cache and re-fetch'), which is genuinely useful, but says nothing about auth requirements, rate limits, or that this is a read-only retrieval (implied but unstated). Partial coverage of a no-annotation tool.

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 one-line summary followed by a compact args block; each line earns its place. The args section is slightly redundant with schema defaults but no sentence 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?

No output schema and no annotations exist, so the description is the sole source of information. It covers inputs well but never describes what a returned 'row' contains or the leaderboard structure, leaving the agent unable to anticipate the response shape.

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: all three parameters are documented, including the valid values for 'board' (coding_agents, chatbots, search_api) which are absent from the schema and not constrained by any enum. Defaults for top and board are restated, which is minor redundancy.

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 the resource clearly (agent leaderboards) and enumerates the three content types it covers (coding agents, chatbots, search APIs). An agent understands the deliverable, but the definition never distinguishes itself from close siblings like aa_leaderboard or aa_benchmark_leaderboard, so the boundary is left to inference.

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?

There is no statement of when to use this tool versus the eleven siblings, several of which (aa_leaderboard, aa_benchmark_leaderboard) sound nearly identical. The only routing clue is the word 'agent' in the description, which the agent must decode on its own.

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 provided, so the description carries the full burden. It discloses the auto-source-selection behavior, that headers warn about incomplete data, that estimates are marked with * and footnoted, and that refresh bypasses cache. Strong behavioral disclosure, though it doesn't state auth needs or rate 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?

Front-loaded with purpose and auto-selection logic, then args in a clear list. Every sentence earns its place, though the eval slug examples in the arg list are slightly verbose.

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 8 params, no annotations, and no output schema, the description covers purpose, source-selection behavior, estimate marking, cache behavior, and all parameters. Missing only auth/rate-limit context or return-format hints, but otherwise complete for an agent to invoke 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 entirely, and it does: it documents all 8 params with meaning beyond types (benchmark accepts key/label/slug, top default 15, fields as comma list overriding defaults, creator substring match, open_weights filter, min_intelligence threshold, include_estimates default True with marking behavior, refresh bypasses cache).

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 (rank) and resource (models on one benchmark) and explicitly names the honesty constraint about source/coverage. Distinct from siblings like aa_leaderboard (general) and aa_model (single model detail).

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 explains the auto-selection hierarchy (700-row leaderboard > curated eval chart > homepage panel) and warns when it falls back to a non-full leaderboard. This tells the agent exactly when this tool is appropriate versus alternatives.

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 behavioral burden. It does add real value by disclosing that every hit embeds a 'How to query' hint (the exact follow-up tool call), which is a non-obvious output behavior. It says nothing about result limits, pagination, ordering, or whether the index is read-only, so the disclosure is partial.

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 one-line purpose, then the key output affordance, then a scoped Args block. Every sentence earns its place and the concrete 'Artificial Analysis Speech to Speech Index' → aa_media example is high-value rather than 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?

For a 4-parameter, annotation-free, output-schema-free search tool, the definition covers purpose, filtering dimensions, and hit contents. It leaves minor gaps around result volume, ordering, and pagination, but nothing that would cause an agent to invoke it incorrectly.

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 query's matching semantics (AND over key/label/aliases/description/tags), enumerates realistic domain values, explains that tag is a narrower filter than domain, and says verbose surfaces what each thing measures. Only the lack of a tag vocabulary or worked examples keeps it short of complete.

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 set: 'Search everything rankable: benchmarks, indexes, derived metrics, arenas.' An agent can tell this is a discovery/search index rather than a leaderboard tool. It does not, however, distinguish itself from the similarly-named sibling aa_search or explain how it relates to aa_benchmark_leaderboard, so sibling differentiation is only partial.

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 Args block implies usage: tokenised AND-match queries, a domain filter, or a narrower tag filter, which tells the agent how to drive the tool. But there is no explicit statement of when to prefer this over aa_search, aa_benchmark_leaderboard, or aa_leaderboard, and no exclusions or prerequisites. Usage is inferable but not 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?

With no annotations, the description carries the full burden and largely meets it: it discloses how missing cells are footnoted so no gap is silent, that arena scores are not cross-comparable, that mixing model types is refused, that refresh bypasses the cache, and that a reproducible spec block is always returned. It does not state auth needs or rate limits, leaving a small gap.

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 purpose and scope are front-loaded and the Args section is well organized, but the opening prose paragraph is long and dense with operational detail that arguably belongs in contextual notes rather than a purpose statement. Most sentences carry information, yet the description leans toward over-specification relative to a concise tool blurb.

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 no annotations, the description covers what an agent needs: input ranges, view modes and their rendered output (columns vs. per-metric deltas), the default metric set, arena behavior, refusal conditions, caching, and the guaranteed spec block. Nothing essential for a correct call 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 and it does: each of the six parameters is documented with accepted values and defaults (metrics accepts 'all'/'benchmarks'/comma lists, view is 'table'/'diff', compact is ignored when metrics is given, spec merges with explicit args, refresh bypasses cache). It adds semantics well beyond the bare schema types.

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 ('Side-by-side comparison of 2-12 models on any benchmark'), names the input domain (language models or arena entries), and mirrors a concrete external artifact (artificialanalysis.ai comparison pages). An agent can distinguish it from aa_leaderboard, aa_model, and aa_pareto 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?

Usage is implied by the compare semantics and edge cases are described (arena-only comparisons render board metrics; mixing a language model with an arena entry is refused with an explanation). However, there is no explicit routing guidance telling the agent when to pick aa_compare over aa_leaderboard, aa_pareto, or aa_model, which is the core 'vs alternatives' question.

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 burden and adds meaningful behavior: returns a compact markdown table sorted by sort, default intelligence; top >15 drops the Creator column; refresh bypasses cache; frontier mode shares code path with aa_pareto. It stops short of stating read-only nature, auth needs, or rate limits, so not full 5.

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 user questions before the Args list, and the Args block is tightly formatted with no redundant sentences. Length is justified by the 16 parameters.

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 16 parameters, no annotations, and no output schema, the description covers output format, default sort, column behavior, caching, and all parameters. It leaves no critical gap for an agent 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 description coverage is 0%, so the description must compensate, and it does: all 16 parameters are documented with defaults, allowed values, units, examples, and semantics (e.g., max_cost_per_task cache-aware, min_speed median output tok/s). It also points to aa_reference for the full sort alias list.

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 ('Rank and filter the ~700 tracked model variants') and positions itself as the default starting point. Answers concrete user questions ('which model is smartest / cheapest / fastest / best value right now') and distinguishes itself from aa_pareto and aa_reference where relevant.

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 says this is the default starting point for leaderboard queries and names alternatives for specific needs: aa_reference for field names, aa_pareto for other x-axis plots. Mode descriptions clarify when to use rank, value, or frontier.

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 burden and does disclose real behavioral traits: refresh bypasses the cache, Elo CI is hidden by default, fuzzy key normalization (text-to-image == text_to_image), and alias acceptance (realtime_voice). It stops short of stating read-only nature or rate limits, but the caching and default-output behavior are genuinely useful context.

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?

A one-line summary is front-loaded before the Args block, and the structured arg list is dense with no filler. The board enumeration is long but each entry is load-bearing; the only mild cost is length.

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, yet the description conveys the key return content (Elo plus 95% CI, selectable columns) so the agent knows what comes back. It could state the return format/row shape more explicitly, but for a leaderboard lookup it is adequately 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?

Schema coverage is 0%, so the description must compensate and it does thoroughly: it enumerates every valid board key plus aliases, explains normalization, gives the top default, lists supported field columns including ci_lower/ci_upper/ci/open_weights/url, and defines open_weights and refresh semantics. This is far more than the bare schema offers.

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 — human-preference arenas for image, video, speech, and music with Elo + 95% CI — which is concrete and distinguishes it from generic leaderboard tools. However, it never explicitly contrasts itself with close siblings like aa_leaderboard or aa_benchmark_leaderboard, so the agent must infer the boundary.

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 through the enumeration of valid board keys, which tells an agent this tool is for media arenas rather than text/benchmark leaderboards. There is no explicit when-to-use/when-not or named alternative, which is a gap given three leaderboard-family 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?

With no annotations, the description carries the full burden and mostly succeeds: it discloses ambiguity handling ('Ambiguous names return a candidate table'), error behavior for invalid sections ('Unknown names error with the valid list'), caching semantics ('refresh: bypass the cache and re-fetch'), and the round-trippable slug in header/footnote. It does not mention auth or whether the call has side effects, which is a minor residual gap.

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 summary sentence, then a short usage sentence, then a compact Args block that keeps each parameter to one to two lines. No filler; every clause carries information an agent needs to invoke the 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?

Despite no output schema and no annotations, the description covers the return categories, the ambiguity path, error cases for bad section names, the slug round-trip, and all inputs. An agent has everything required to call it correctly and to interpret an ambiguous result.

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 fully — and it does: it documents query's fuzzy matching and ambiguity fallback, enumerates the valid section names, gives the default set, notes the 'specs = identity' alias, and explains that refresh bypasses the cache. All three parameters are meaningfully specified beyond the bare types 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 precisely what is returned for a single resource — 'One model's full digest: specs, indices, benchmark scores, pricing and speed' — and immediately differentiates from the leaderboard/search siblings. An agent can tell that this is the deep single-model view rather than a list view 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?

Explicitly positions the tool in a workflow: 'Use after aa_leaderboard/aa_search when you need everything about a single model,' naming the alternatives. It stops short of stating when NOT to use it (e.g., for multiple models use aa_compare), so the exclusion side is inferred rather than stated.

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 well: it defines the dominance rule, the ordering (x ascending), the default cheapest-first truncation, that deprecated rows are excluded by default, and that refresh bypasses the cache. It does not state freshness/rate-limit behavior or the exact response shape, but the cached-vs-refreshed distinction and default filtering are real disclosures.

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 definition and dominance rule, then organized into site-view mapping and Args sections so an agent can scan it. The site-view block is slightly verbose for three examples and the smart-quote formatting is noisy, but no sentence is purely 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?

No output schema exists, and the description does explain what is returned (non-dominated models, x-ascending order, knee line, coverage) as well as default truncation and filtering. It stops short of describing the concrete response structure or error behavior, leaving a small gap for a 10-parameter analytical 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% and all 10 parameters are undocumented in the schema, yet the Args block defines every one, including enumerated values for x (cost_per_task, index_total_cost, out_tokens_per_task, time_per_task, context_tokens, params_b, ttft, price_in, price_out) and example values for score. This is exactly the compensation the zero-coverage schema requires.

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 (compute the Pareto frontier of any score against any trade-off axis) and quantifies the output (frontier points plus a knee and coverage). This is clearly distinguishable from aa_leaderboard or aa_compare, which rank rather than compute a non-dominated set.

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 tells the agent it is 'Always available — no per-benchmark tool needed' and maps three concrete site views onto parameter combinations, which is strong when-to-use context. It never excludes or routes against specific siblings such as aa_compare, so it stops short of full 5-level routing guidance.

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 present, the description carries the full behavioral burden and does meaningfully cover it: it discloses the default result set when no arguments are given, that a cache exists and ``refresh`` bypasses it, that lower-is-better sort keys order ascending, and the default row count. It omits auth requirements, rate limits, and any failure behavior, so it is strong but not exhaustive for an unannotated tool.

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 mode-selection rule is front-loaded in the first paragraph before the Args list, so the most decision-relevant information comes first. The parameter block is long but each line adds distinct semantics rather than restating the schema, so little is wasted; a tighter single paragraph could have trimmed a few lines.

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, so the description must convey the return shape, and it does name the key outputs ($/task, precision, the 1,200-row provider board). Combined with the mode rules and full parameter documentation, an agent has enough to call it correctly, though a note on result shape for the board mode (columns, pagination) would close the remaining gap.

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%, yet all eight parameters are explained in the Args block with genuine meaning beyond the schema: ``sort`` enumerates six keys plus the lower-is-better ascending rule, ``fields`` lists the extra columns it unlocks (cache_read, discount, e2e, etc.), ``host`` gives an example substring, and ``min_context``/``open_weights`` state their filtering semantics. This fully compensates for the empty schema descriptions.

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 line states the resource and the data it exposes (per-host pricing, precision, speed, feature flags), and the body distinguishes three operating modes: per-model endpoints, the host/filtered provider board, and the global cheapest-endpoint fallback. It never references the sibling tools (aa_model, aa_leaderboard) that an agent might confuse it with, 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?

Explicit routing logic inside the tool: pass ``model`` for one model's serving endpoints, ``host``/filters for the provider board, and 'with neither, returns the cheapest endpoints globally.' That resolves the main ambiguity about how to invoke it. It gives no guidance on when to prefer this over siblings like aa_model or aa_leaderboard, which keeps it from a 5.

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 must carry the behavioral load. It discloses two important traits: token expense and cache-bypass via refresh. It doesn't say whether it's read-only, nor whether large result sets are truncated or how errors surface, leaving meaningful 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?

An args list with one line per parameter is appropriately structured for a five-parameter tool. The kind line enumerates nine values in one long sentence, but nothing 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?

Explains inputs well but omits output shape and return semantics, and the schema offers no help (0% coverage, no output schema). For a generic escape hatch the input docs are decent, but an agent still lacks a picture of what it gets back.

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 largely does: it enumerates the valid kind values, explains query's meaning per kind with examples, defines fields for top-level projection, and notes top's cap of 5 with default 1.

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?

Describes itself as a raw JSON escape hatch that returns unfiltered records, contrasted with a family of table tools. It's clear it's a generic low-level fetcher, though it doesn't state a single verb+resource precisely because it's a multi-kind passthrough.

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 steers the agent away: 'prefer the table tools, token-expensive'. This gives a clear when-not-to-use signal. What's missing is a positive condition for when the escape hatch is actually the right choice.

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 burden, and it does disclose a meaningful trait: 'No network' signals static, offline, deterministic, side-effect-free retrieval. That is genuinely beyond structured data. It does not discuss output size, caching, or error behavior, keeping it from a 5.

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 the key constraint ('Static reference text', 'No network') are front-loaded in the first two sentences, and the argument list is compact. The stray blank lines and 'Args:' block add minor formatting noise but no wasted prose.

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, no-annotation, no-output-schema documentation tool, the description covers what it returns, its offline nature, and every valid topic value. The only omission is any hint about the shape or length of the returned reference text, which is minor.

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% and the schema declares no enum for `topic`, so the description is the only source of valid values. It lists all ten accepted topics (overview, indexes, benchmarks, pricing, speed, providers, media, fields, sources, all) plus the default and the 'fields' alias caveat, fully compensating for the schema 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 exactly what the tool returns (static reference text) and enumerates its subject matter: tool routing, metric/eval definitions, provenance. The phrase 'which tool answers what' explicitly positions it as the meta/routing doc relative to the many aa_* siblings, so an agent can distinguish it 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?

'Use to learn what the fields mean and which tool answers what' gives a clear affirmative trigger for invocation, and 'No network' implies it is the fallback for terminology questions rather than data. It stops short of naming exclusions (e.g., don't call for live numbers – use aa_leaderboard), so it is not a full 5.

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 burden and does add real behavioral context: it is "cheap," results are cached and `refresh` bypasses the cache, a slug is always returned, and media/speech boards are included with their board label. It never mentions auth requirements, rate limits, or error/empty-result behavior, so it is not fully transparent.

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 and routing instruction in the first sentence, and the Args block is compact. The media/speech sentence is slightly defensive prose, but it justifies a real edge case rather than being 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?

For a five-parameter, no-annotation, no-output-schema tool, the description covers all parameters, the cache model, and the guarantee of a slug return (plus board labels for media models). It stops short of describing the shape of returned rows or how many results `top` can safely request.

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 the Args block documents all five parameters with meaning beyond their names: query is a fuzzy name or partial slug (with an example), creator is a substring filter, open_weights keeps only one weight class, top is a row count with default, refresh bypasses cache. It omits acceptable query syntax limits and slug format conventions, keeping it from a 5.

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+scope: a name-to-slug resolver, with the explicit routing claim that it should be called first when a name is uncertain. It is clearly distinguishable from detail-oriented siblings like aa_model or aa_compare 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?

"Call this first whenever a name is uncertain" gives a concrete trigger condition and an ordering rule relative to the next tool call. It lacks explicit when-not guidance (e.g., when a name is already known to be an exact slug), so it falls just short of the top band.

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