Launch Tape

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds useful constraints — max 1500 compact trades, first 30 minutes after graduation, history starting October 3, 2026, and variable dataset coverage — but does not explain what 'compact' means or what the response shape is.

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?

Only three sentences and no filler, so it is concise. But the first sentence is grammatically broken and front-loads ambiguous information instead of the core action, which weakens structure.

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, four parameters, and only 25% schema description coverage, the description should carry more weight. It omits what the tool returns, how 'mint' is interpreted, and how 'api_key' is used, leaving significant gaps 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 only 25%, so the description needs to compensate. It does clarify that 'minutes' relates to the first 30 minutes after graduation and that 'day' should be sourced via days_available, but it says nothing about 'mint' or 'api_key' semantics beyond their names.

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 never clearly states the verb or resource — 'One graduate and at most 1500 compact trades' is fragmented and ambiguous about whether the tool returns trades, graduates, or both. It implies trade retrieval via the tool name and 'compact trades', but an agent cannot confidently tell what the call produces or how it differs from siblings like day_full_stats or lookup_coin.

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 one concrete routing hint: 'Use days_available for the exported UTC day range,' which is helpful. However, there is no explicit when-to-use vs. alternatives (e.g., day_full_stats) and no when-not 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?

The annotations already establish that this is a read-only, idempotent, non-destructive tool. The description adds valuable behavior beyond the annotations: it caps results at 20 rows, notes that coverage varies by dataset, and states that history starts October 3, 2026.

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 compact and front-loads the key fact that it returns real preview rows capped at 20. Each sentence carries relevant constraint or orientation information, with little wasted text.

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 preview tool with no output schema, the description covers the main behavioral facts an agent needs: row limit, supported datasets, history boundary, coverage variability, and the related days_available tool. It does not describe the returned row shape, but that is a minor gap here.

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%, but the single dataset parameter has an enum listing graduates, gradtrades, and pregrad. The description repeats those values and notes that coverage varies by dataset, but it does not explain further distinctions among the datasets or add much detail about the parameter beyond the enum.

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 concrete outcome: returning real preview rows, capped at 20, for three named datasets. It also references days_available for exported UTC day ranges, which helps distinguish this preview tool from a date-range utility, though it does not define itself against the other data-query 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?

It gives useful constraints, namely that only graduates, gradtrades, and pregrad have site previews and that days_available should be used for exported UTC day ranges. However, it does not explicitly say when to choose data_preview over other data-oriented siblings such as day_full_stats or graduation_stats.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds two real behavioral facts beyond the annotations — the history start date (October 3, 2026) and that coverage varies by dataset — which an agent would otherwise not know, but omits what happens for out-of-range days or partial-coverage days, which is the follow-on question this caveat invites.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no filler; the datasets and the days_available cross-reference are front-loaded. The only weakness is that the lead sentence is a bare list with no verb, so it reads as a fragment rather than a definition.

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 carries the burden of explaining what comes back; listing the four dataset groups partially does that but says nothing about response shape, granularity, or whether empty/partial days return sparse or error results. For a two-parameter read tool this is adequate but leaves real gaps.

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 50%: 'day' is documented in the schema, while 'api_key' is undocumented (though its 27-char constraint and name make it self-evident). The description's pointer to days_available meaningfully aids selection of a valid 'day' value, which is the only non-trivial parameter, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the datasets included (graduation stats, 10-minute buyers, dev-share bands, touched outcome distributions) but never states a verb or a coherent one-line purpose — it's a noun-phrase list rather than 'Get the full per-day snapshot for X'. An agent can infer it's a per-day aggregate report, but separating it from the sibling graduation_stats requires guessing.

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 one concrete routing rule — 'Use days_available for the exported UTC day range' — which is genuinely useful and names the correct sibling. However, it offers no guidance on when to prefer this over graduation_stats or wallet_day, which are the closest overlapping siblings, so usage is only partially disambiguated.

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

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add context — and it does: the data comes from public manifests, history begins October 3, 2026, and coverage varies by dataset. That coverage caveat is genuinely useful for interpreting sparse results. It stops short of describing pagination or ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with what is returned and immediately followed by the coverage caveat. The final sentence is largely redundant with the opening and could be dropped or replaced with real usage guidance.

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 parameters, the description carries the return-value burden and does so adequately by naming both returned fields and the per-dataset grouping. The history start date and varying coverage round out what an agent needs to interpret an empty or partial 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description's mention of per-dataset scope correctly signals that the output is keyed by dataset even though no input selects one.

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 and payload: exported UTC days plus byte sizes per dataset, sourced from public manifests. An agent knows exactly what it gets back. It does not, however, contrast itself with siblings like day_full_stats or wallet_day, which also deal with day-scoped data.

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 only usage sentence, 'Use days_available for the exported UTC day range,' just restates the tool name and adds no decision criteria. There is no guidance on when to call this versus day_full_stats, data_preview, or wallet_day, and no stated prerequisite (e.g., call this first to discover valid days).

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds useful behavioral context—history starting October 3, 2026, dataset coverage variability, and the 'followed, gap-free, full tapes only' filter—but these constraints are cryptic and unexplained.

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 compact and front-loads the day scope, but packs multiple opaque metrics and filter conditions into dense clauses ('positive/doubled 30-minute changes', 'followed, gap-free, full tapes only') without explanation. Conciseness is achieved at the cost of comprehensibility.

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 must convey what the tool returns; it names several metrics but does not explain their format or meaning. History and coverage notes are helpful, but key domain terms remain undefined for an uninitiated agent.

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 `day` parameter is fully documented in the schema, including its default. The description adds no additional meaning about the parameter beyond restating UTC-day semantics, so 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 indicates the resource (statistics for a single UTC day: graduate counts, 30-minute changes, median curve fill) but the phrasing is domain jargon rather than a clear statement of what the tool returns. It does not distinguish itself from the sibling tool day_full_stats, leaving the agent to guess which one to call.

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

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

There is no guidance on when to use this tool versus day_full_stats or wallet_day. The only routing instruction is 'Use days_available for the exported UTC day range,' which points to a helper tool rather than explaining selection criteria for this tool.

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

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

Annotations already establish read-only, idempotent, closed-world, non-destructive behavior, so the description is not burdened with the safety profile. It does add non-obvious facts a caller could not infer: history begins October 3, 2026, and coverage limits vary by dataset rather than being uniform. It does not indicate whether results are static or refreshed, but that 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?

Three short sentences, with the highest-value content (what is covered, the history start date) placed first. The opening fragment is slightly elliptical and reads as a list of contents, but no sentence is padded or redundant.

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 zero parameters and no output schema, the description carries the burden of telling the agent what comes back, and it does so by listing the content categories plus the coverage caveat. The main omission is any sense of the response's shape or size — e.g., whether it returns a single summary record or a per-dataset list — which matters for a no-argument catalog call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes no parameters, so per the baseline this scores 4. The description correctly introduces no parameter discussion and instead names a sibling tool for the parameterized question an agent might mistakenly expect here.

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 enumerates the concrete contents of the overview: what Launch Tape records, dataset descriptions, USD plan prices, and coverage limits. That is enough for an agent to know this is the catalog/pricing reference tool. It falls short of 5 because the opening is a noun-phrase fragment rather than a verb+resource statement, and it does not contrast with my_plan, which likely also carries plan/pricing information.

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 one explicit routing instruction: use days_available for the exported UTC day range, which correctly diverts a related question to a sibling. Beyond that, usage is only implied — nothing says whether to call this before other tools or how it differs from my_plan or data_preview when the agent needs plan or dataset facts.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description rightly spends its words elsewhere: a hard result cap ('at most 20 matches'), a data start date, and an explicit warning that coverage varies by dataset. These are non-obvious traits an agent cannot get from the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight clauses with no filler: purpose plus result cap first, then temporal coverage caveats, then the routing hint to days_available. Front-loaded and appropriately sized for the tool's simplicity.

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 two-parameter read with no output schema, the description covers the essentials an agent needs to call it correctly: exact-match semantics, a result ceiling, the earliest available date, and a variability warning. It stops short of saying what happens if a symbol matches multiple mints across the day, which would have closed 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 coverage is 50% — mint_or_symbol has no schema description at all, and the description partially compensates by specifying 'exact' matching (meaningful for symbol vs mint disambiguation). The day parameter is documented in the schema, including its default, so the description adds little there.

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 ('Public graduate facts'), the lookup key ('exact mint or symbol'), and the scope ('one UTC day'). The 'exact' qualifier separates it from broader listing tools, though it never names the closest sibling (coin_trades) to draw the contrast.

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 routes the agent to days_available when it needs the valid date range, which is a real usage instruction. However, there is no guidance on when to prefer this over coin_trades or day_full_stats, so the agent must infer the boundary from names alone.

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

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

Annotations already establish this as a read-only, idempotent, non-destructive operation. The description adds useful context about history start date and dataset-dependent coverage, though it does not mention authentication behavior or what happens with an invalid key.

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 short and front-loads the returned information before the caveat and sibling pointer. The first sentence is a fragment rather than a direct statement, 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?

For a simple read-only status tool with rich annotations and no output schema, the description covers the key returned concepts and data coverage caveats. The remaining gap is that the sole API key parameter is never explained.

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 one parameter, api_key, and schema description coverage is 0%, so the description needs to compensate. It never mentions the API key, its required status, or its purpose, leaving the only parameter entirely undocumented in text.

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 information returned: purchased scope, expiry, and remaining calls. It lacks an explicit verb, but an agent can identify it as a plan/subscription status tool and distinguish it from days_available via the explicit routing note.

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 usage context for plan status and explicitly points to days_available for the exported UTC day range. It does not provide explicit when-not conditions, but the sibling handoff is clear enough for correct selection.

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 read-only, idempotent, non-destructive, and closed-world behavior. The description adds important context beyond annotations: it is a no-real-trade replay, uses conservative reserve fills and costs, has per-tier rate/quota limits, and has partial historical coverage starting October 3, 2026.

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 the core action and then efficiently layers quota, simulation, historical-coverage, and date-range guidance. Every sentence carries useful information for an agent deciding whether and how to call 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?

The description covers important operational context such as quotas, date limits, history start, dataset variability, and the absence of real trades. For a complex nested-rule tool with no output schema, however, it does not explain what a replay result contains or define the rule fields, leaving notable gaps 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 moderate at 60%, and the description helps with date-range semantics by pointing to days_available and noting the 10-day cap for covered days. However, it does not explain the core rule object fields such as entry filters, exit conditions, or position_sol, leaving the most important nested parameter semantics to the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: replay a structured rule on recorded PumpSwap trades. It also clarifies that this is a simulation with conservative reserve fills and costs and that no real trades occur, which distinguishes it from data-retrieval 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?

It gives concrete usage constraints by access tier, including free daily limits and paid covered-day/key quota limits, plus a maximum of 10 days per call. It also directs the agent to days_available for the exported UTC day range, though it does not explicitly say when to choose this tool over all other siblings.

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

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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description correctly focuses on dataset-specific traits: the 50-record ceiling, the October 3, 2026 history boundary, and per-dataset coverage variance. It omits any mention of authentication failure behavior or what happens when the requested day predates the coverage window, which are the remaining real risks for a caller.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with zero padding; the record cap and history boundary are front-loaded before the pointer to days_available. Every sentence carries distinct information -- constraint, temporal boundary, and routing.

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 25% parameter coverage, the description should explain more of the call contract. It never says what a 'wallet observation' contains or what 'top' ranks by, leaving an agent unable to predict results or choose `by` meaningfully -- adequate but with clear gaps for a 4-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 only 25% -- only `day` is documented in the schema, so the description must carry `n`, `by`, and `api_key`. It repeats the 50-record cap already encoded as the schema maximum but says nothing about the `by` enum values (realizedSol vs solIn), which is the single most consequential parameter choice, nor about ranking direction or the api_key requirement.

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 and scope: top daily wallet observations capped at 50, with a history start date. It is clear what the tool returns, but it never distinguishes itself from the close sibling wallet_day, so an agent must guess which of the two to use for per-wallet vs ranked-list queries.

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 routes the agent to days_available to discover the exported UTC day range, which is a concrete when-to-use-an-alternative instruction. It stops short of saying when NOT to use this tool (e.g., for a single wallet's detail, use wallet_day) or what to do if the requested day is outside coverage.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the description's job is to add beyond that. It does contribute a hard row cap and a history start date (October 3, 2026) plus the warning that coverage varies, but it never says whether hitting 100 rows means truncation or sampling, which matters for a bounded read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with no filler; the subject and row cap are front-loaded and the cross-reference comes last where a reader needs it.

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 is the only source of shape information, yet 'observations' is never unpacked into what fields come back. Combined with two undocumented parameters and unspecified truncation behavior at the 100-row cap, it is adequate but not 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 only 33%, so the description must carry the undocumented majority. It clarifies that the day is an exported UTC day and defers range discovery to days_available, but leaves 'wallet' (format, single vs list) and 'api_key' entirely unaddressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names the resource precisely ('Wallet and walletcoin daily observations') and adds a scope constraint (at most 100 rows) plus a date floor. It does not explicitly contrast with close siblings like day_full_stats, but the row cap and per-wallet focus give an agent enough to distinguish it.

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 final sentence routes the agent to days_available to discover the valid UTC day range, which is genuine usage guidance. However, there is no statement of when to prefer this over day_full_stats or coin_trades, so the choice among aggregate-style siblings 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.