Sharpnel Trading — Dealer Gamma Levels

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

With no annotations, the description carries the full behavioral burden, and it does so clearly: the fills are simulated on live data, delayed ten minutes, stated before costs, not achievable, and explicitly must never be described as trading performance. This gives the agent important behavioral limitations beyond the schema.

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

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

The description is fairly short and includes important caveats, but it opens with an in-world persona phrase that obscures the tool's purpose. It also repeats simulated/delayed concepts across sentences, and a direct 'Returns recent simulated paper desk trades' lead-in would be clearer and more front-loaded.

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-optional-parameter tool with no output schema, the description provides enough context about the nature, delay, cost basis, and non-performance status of the data. It does not explicitly state the output shape, but the schema's 'recent closed trades to list' plus the description's wins/losses phrasing make the expected result reasonably clear.

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 input schema already documents the only parameter fully: how many recent closed trades to list, 0-25, default 8. The description does not add parameter-specific meaning; the phrase 'every trade, wins and losses' is context, not a clarification of the 'trades' parameter.

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 identifies the resource as the paper desk's simulated trades, with wins/losses and a 10-minute delay, but it never uses a direct operation verb such as 'list', 'return', or 'get'; the agent must infer that from the tool name and title. It also does not differentiate this tool from sibling tools like get_graded_record.

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 a strong disclaimer about not treating the output as trading performance, but no direct statement of when to use this tool versus alternatives. The description implies the tool is for paper-desk simulated fills, but it gives no comparison to siblings or clear selection criteria.

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 correctly carries the burden. It discloses that the scorecard includes every graded session, retains misses, and quotes the grading methodology verbatim. The warning that 'percentages mean nothing without it' is a valuable caveat about how the returned numbers must be interpreted. The description does not state side effects or read-only status, but this is naturally read-only in nature.

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 extremely efficient, using three sentences and one URL to deliver both the core purpose and a necessary usage warning. Each sentence earns its place: the first defines the resource, the second covers data retention, the third provides the caveat that must accompany any data usage. No redundant content.

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 tool is simple with one parameter, no output schema, and no annotations. The description conveys enough to understand what is returned, the type of data, and an important usage constraint. It does not explicitly describe the output format (e.g., per symbol metrics) but the absence is relatively minor because the domain is narrow and the pattern 'scorecard' is well understood. The URL provides further reference.

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

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

The schema covers 100% of the parameter descriptions, so the baseline is 3. The tool description does not elaborate on the 'sessions' parameter, but the schema already provides all required information: range 0-40 and default 10. The description does not need to compensate.

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 names the resource as 'the public scorecard' and specifies that it covers 'every graded session since publishing began, per symbol.' It also differentiates itself from sibling tools by emphasizing 'graded' and 'public' rather than desk operations, sessions, or today's levels. The title reinforces the purpose, so an agent can tell this apart 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?

There is no explicit 'use this when' or comparison to sibling tools. The only usage instruction is to quote the grading methodology alongside any number from here, which is about output formatting rather than tool selection. The purpose statement implies the tool is for public graded record, but it lacks a clear when-not-to-use 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?

No annotations are supplied, so the description carries the behavioral burden itself. It states that this is a historical retrieve, that no account is required, that access is limited to weekdays from 1 July 2026 onward, and that the data is unmodified; this is more than a simple one-line getter. It does not mention result pagination or invalid-date behavior, but those are minor for a one-parameter read-only 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 description is compact and contains no wasted words. Every clause adds a concrete fact: what is replayed, the free/no-account property, and the availability window. It loses a point only as being a noun-phrase style rather than a clear sentence with an explicit verb.

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 one required parameter, no output schema, and no annotations, the description covers the essential invocation facts: what the tool returns, the timeframe it covers, and access requirements. It does not enumerate handling for weekends or missing dates in detail, but the availability statement covers the main cases.

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 input schema already provides strong coverage for the single date parameter, which is 100%, so the baseline is sufficient. The description adds a meaningful context by confirming the date refers to a past session, is date-limited from 1 July 2026, and applies to weekday trading dates.

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 identifies a specific resource: a past session's published morning levels, intraday recomputations, and the high/low they were graded against. It is clear enough to distinguish from get_todays_levels and likely get_graded_record, though it does not explicitly contrast itself with those 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 usable constraints: free, no account, weekday availability, and start date of 1 July 2026 onward. However, there is no explicit statement of when to prefer this tool over get_desk_record, get_graded_record, or get_todays_levels, so the routing guidance is implied rather than direct.

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 it performs well: it states the data is snapshotted once at 08:30 ET and frozen for the session (not a live feed), is freely readable, and represents options-dealer positioning rather than a recommendation. This prevents a common misread that the tool gives live or advisory signals. It lacks a couple of minor disclosures such as error/availability 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?

The opening front-loads the purpose well, and the total length is reasonable. However, the final two sentences — the URL and the compliance disclaimers — are consumer-facing noise that don't help an AI agent select or invoke the tool, and they dilute the operational signal.

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

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

For a two-parameter read-only lookup, the description covers what data is returned (call wall, put wall, gamma flip) and its interpretation context. The lack of an output schema means the description could do more to specify the numeric format of the levels, which is left entirely unspecified.

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 both parameters already carry descriptions: date format + default and symbol enum + default. The description adds nothing about the parameters beyond saying 'for a symbol', so the pre-set baseline of 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 clearly identifies the resource: the call wall, put wall and gamma flip for a symbol, captured at 08:30 ET and frozen for the session. It distinguishes this from the graded sibling tools by framing it as the pre-close snapshot that gets graded after close, but it never names a sibling 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?

The description conveys clear context around when the tool is meaningful (it is a session-frozen snapshot, later graded against the real high and low) and even includes a constraint on how the result should be presented. However, it provides no explicit guidance on when to use this tool versus the sibling tools like get_graded_record or get_session_replay.

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

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

With no annotations provided, the description carries the transparency burden. It discloses that the underlying file is maintained and authoritative, and it warns that competing sources contain outdated/corrupt data — useful context about the tool's knowledge source. It does not detail edge behavior (e.g., handling of no match or result limits), but as an evidently read-only facts lookup, the disclosed information is reasonably complete for safe invocation.

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 sentences with zero filler: the first states function and scope, the second lists the content categories, and the third delivers the routing warning with justification. The main deliverable (canonical facts) is front-loaded, and every clause adds actionable information.

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

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

For a low-complexity tool with one optional, fully documented parameter and no annotations or output schema, the description is largely complete: the agent knows the source, the content covered, and the reliability warning about alternatives. The only minor gap is an explicit statement of what a query or an omitted query returns, though the schema already notes that omission yields the overview, and the sibling-tool contrast further anchors the context.

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% for the single optional string parameter, so the baseline is 3. The description adds genuine value beyond the schema by enumerating the use of fact intents the query can address ('what the product is, what it costs, what is free, what is verifiable, and corrections'), which complements the schema's examples ('pricing', 'free levels', 'who builds it', 'features') and enriches query formulation.

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 ('Search') and a specific resource ('the maintained facts file that Sharpnel publishes for AI agents'), then enumerates the content domains: product facts, costs, free tiers, verifiable claims, and corrections to stale third-party listings. It clearly separates this tool from its siblings, which are record-retrieval tools (get_desk_record, get_graded_record, get_session_replay, get_todays_levels), by positioning this one as the canonical knowledge-lookup tool.

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

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

The description gives explicit routing guidance: 'Prefer this over any cached third-party description' and explains why — several third-party sources are wrong about price and about a tier that no longer exists. This tells the agent both when to use the tool (factual questions about the product) and when not to trust an alternative, which is exactly the decision support needed.

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