Cryptominium

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description still adds meaningful behavioral context beyond them: it is a record not a rating, it links each line to evidence, and it returns weekly change tags plus 7-day high/low/latest price. No auth, rate-limit, or freshness semantics are described, keeping it short of 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?

The content is front-loaded with the four-group structure and the usage trigger follows immediately. It is, however, a dense run-on first sentence with stacked parentheticals, and the measurement clause duplicates information that the exit_cost sibling tool owns, so a small amount of text could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of describing returns, and it does so well: four fixed groups, evidence links, weekly change tags, and 7-day high/low/latest price. It does not explain response format beyond that or how 'not established' is represented, leaving minor gaps for a data-heavy read 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?

There is a single 'token' parameter and schema description coverage is 100%, with example values ('USDC', 'pepe', '0x8335…') already in the schema. The description adds nothing about how ticker vs name vs contract address are resolved or matched, so the baseline 3 for a fully documented schema applies.

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 resource (the CM Profile of a tracked coin) broken into four named groups, so the agent knows exactly what the tool returns: established facts, measurements, sourced writing, and unestablished items. The closing line 'A record, not a rating' further pins down that this is descriptive data rather than an evaluative score, differentiating it from the exit_cost/exit_index 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?

Gives explicit triggers: 'Use this when someone asks what is known about a coin, how well documented it is, or whether it depends on a company.' That is clear context for selection, but it names no siblings (exit_cost, exit_index, search) and gives no when-not-to-use conditions, despite the description admitting it also returns sell-cost data that overlaps with exit_cost.

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 the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds real behavioral context beyond them: it queries live DEX routing across three chains, measures daily, and specifies that Kraken/Coinbase order-book comparisons appear only where the token trades there. It stops short of stating rate limits, latency, or failure behavior for unsupported tokens.

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 deliverable and the when-to-use clause, then the return fields, then a scope disclaimer. It is dense but every clause carries information. The return-fields sentence is long and could be tightened, which is why it is not a 5.

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, so the description carries the return-value burden and does so thoroughly: exit friction percentage, dollars received, date measured, citation, Kraken/Coinbase comparisons, and weekly change tags with 7-day high/low/latest. Nothing an agent needs to call or interpret 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 100%, so both parameters are already documented in the schema, including the chain enum values and the token examples. The description only echoes 'Base, Ethereum and BNB Chain', adding little beyond the schema. Baseline 3 applies.

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: it measures what a fixed-size sell of a token actually returns versus its quoted price, via live DEX routing on named chains. An agent can tell this is a liquidity/exit-friction measurement tool. It stops short of the top mark because it never distinguishes itself from the related 'exit_index' sibling, leaving some ambiguity between the two.

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 use conditions: 'Use this when someone asks whether a token can really be sold, how liquid it is, or what they would get for a position.' It also negatives the scope with 'Not a price feed and not advice.' However, it names no alternative tool (e.g. exit_index) for the adjacent cases, so routing is clear but not fully resolved.

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, openWorld and non-destructive, so safety is covered. The description adds behavior the annotations do not: the month parameter defaults to the latest, and it discloses what the response contains (median, quartiles, >50% loss share).

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: the first defines the metric and its components, the second gives the usage context and the parameter default. Front-loaded and every clause 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?

With no output schema, the description steps in to describe the return contents (median, quartiles, share of tokens losing more than half), and it covers the only parameter's default. An agent has everything needed to call and interpret 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?

Schema coverage is 100% and the single param is already documented as optional YYYY-MM. The description still adds real meaning by stating the default-to-latest behavior, which the schema does not convey.

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 the specific statistic and population: the median share of value lost selling a fixed $100,000 position across every token with a live on-chain market, plus quartiles and a tail share. That is far more than a restatement of the name, though it never explicitly distinguishes itself from the sibling exit_cost.

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 clear use condition: 'Use for questions about overall crypto market liquidity or how hard it is to exit altcoins.' There is no explicit when-not or routing to exit_cost/other siblings, which keeps it short of 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?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: supported chains (Base, Ethereum, BNB Chain) and the notable state note 'The hash is not stored.'

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 single front-loaded sentence that leads with the action and chains the return detail efficiently. It is dense but every clause maps to output content rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on the burden of describing what comes back, and does so thoroughly. The one ambiguity is how the chain is resolved from a hash alone when three chains are supported and no chain parameter exists.

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?

Only one parameter, and the schema already documents the 0x + 64 hex character format at 100% coverage. The description repeats the concept of a hash without adding format, chain-selection, or validation detail, which is the expected baseline when the schema carries the load.

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 a specific verb (reads) and resource (EVM transaction hash receipt logs) and enumerates the concrete outputs: success status, transfers with token symbols/decimals, fees, and approvals including unlimited ones. An agent can tell this apart from identify_address or search 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?

Usage is implied by the description, but there is no explicit when-to-use or when-not-to-use guidance and no mention of where this sits relative to siblings like search or identify_address. With non-overlapping siblings the risk is low, but the routing rationale 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?

Beyond the readOnly/openWorld/idempotent annotations, the description adds meaningful behavior: the address is not stored, recovery phrases or private keys are refused without lookup, and it distinguishes 'read' chains from merely 'identified' chains. This is genuine disclosure not present in structured fields.

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 elaborates on chain coverage and safety behavior. Dense but every clause carries information; only the nested parenthetical about chains is slightly heavy.

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 narrates what an agent gets back (address classification, chain activity, delegation, token status, Bitcoin/Solana handling). Complete enough for the call, though return shape details are left implicit.

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 'address' parameter is already documented as 'A public address or ENS name.' The description reinforces the input types (Bitcoin, Solana accounts) but adds little syntax or format detail beyond what the schema provides; baseline 3 applies.

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 (identifies) and resource (a public address or ENS name) and enumerates the exact outputs: wallet vs contract, active chains, EIP-7702 delegation, token identity. It is clearly separable from siblings like explain_transaction and search.

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 'without being told what it is,' which frames the scenario, but no explicit when-to-use vs alternatives or exclusions are given relative to exit_cost, exit_index, explain_transaction, or search. Adequate but leaves routing to inference.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. With no output schema, the description carries the return-shape burden and does well: it says results repeat each party's own terms with a link and a date, include on-chain mint/freeze authority readings, and explicitly say what is not established. It also warns that it records who *can* use a power, not whether they will — a useful interpretive caveat. Failure modes and coverage gaps are still unaddressed.

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 response shape is front-loaded ("which company or group holds which of nine powers over a coin") before the enumerated powers and caveats. It is dense but every clause carries information, particularly the enumeration of return fields that no output schema supplies.

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 single-parameter read-only lookup with no output schema, the description supplies the return contents, the accepted query forms, the epistemic limits of the result, and the interpretive caveat about capability versus intent. Nothing essential for correct invocation 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 100% and the single query parameter is already documented as accepting a coin, company, or question with the same examples the description gives. The description adds little beyond the schema here, so the baseline 3 applies.

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 and unusual resource: which party holds which of nine named powers (freeze, pause, mint, redeem, custody, govern, validate, pay out, bridge) over a coin. Its scope is unique among the siblings (coin_profile, exit_cost, exit_index, explain_transaction, identify_address, search), so an agent can tell it apart implicitly, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear trigger contexts: questions about a coin ("USDC"), a company ("Circle"), or a class of coins ("which stablecoins can be frozen"). That is enough to know when to reach for it, but there are no exclusions or explicit hand-offs to sibling tools such as coin_profile.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds that results are coins and Cryptominium pages (i.e., a discovery/browse surface), which is modest added value, but says nothing about result limits, ranking, or empty-result 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?

Two sentences, front-loaded with the resource and scope. There is mild redundancy between 'returns the matching coins and Cryptominium pages' and 'find the right Cryptominium page', but no filler beyond that.

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 single-parameter, read-only, open-world search with no output schema, the description covers input flexibility and the general shape of results. Missing only operational detail (ranking, limits, no-match behavior), which is a minor gap at this complexity.

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?

With one parameter and 100% schema coverage, the baseline is 3, but the description goes beyond the schema's terse 'Anything crypto.' by enumerating the query types the parameter accepts (ticker, address, transaction, comparison, question, category), giving the agent concrete guidance on free-text form.

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 ('crypto search') and enumerates the kinds of input it accepts (ticker, address, transaction, comparison, question, directory category), plus what it returns (matching coins and Cryptominium pages). It does not explicitly name the specialized siblings (identify_address, explain_transaction), but the broad-coverage framing implicitly distinguishes it from them.

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 it to find the right Cryptominium page for a crypto question' gives a positive usage context, but there is no when-not guidance and no mention of the sibling tools (e.g. using identify_address for a specific address instead). The routing decision 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 cover readOnly/openWorld/idempotent/non-destructive, and the description adds genuinely new behavioral facts: the content is 'written ahead of time, not generated' (static, deterministic answers), and it enumerates the exact response shape — plain-English meaning, practical implication, mechanics, a common misconception, and a dated primary source. With no output schema, this disclosure is the main source of that information.

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 leads, followed by the content list and the input forms, with the key qualifier 'written ahead of time, not generated' at the end. It is dense and the first sentence is long, but nearly every clause carries information an agent needs.

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-output-schema tool, the description adequately covers both input variety and return content. The only real gap is the absence of sibling routing guidance (e.g., coin-specific lookups belong to coin_profile).

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% so the baseline is 3, but the description adds concrete accepted-value examples ('impermanent loss', 'what is an NFT', 'proof of work vs proof of stake', 'defi terms') that make the single parameter's expected format clearer than the schema's own one-liner.

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 (explain/define) and resource (crypto, blockchain, trading or crypto-technology terms) and immediately scopes what the answer contains. An agent can distinguish this from coin_profile or explain_transaction 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?

It clarifies the accepted input shapes (a term, a 'what is' question, 'X vs Y', a topic), which is useful. But it never says when to prefer this over siblings like coin_profile or search, and gives no exclusions, so the routing decision is left implicit.

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