mcp-server

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds that the data is free USGS/public, which is useful provenance context, but does not disclose update frequency, freshness, geographic scope, or rate limits. With annotations carrying the behavior load, this is adequate but not rich.

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 a single efficient sentence that front-loads the tool's domain and then enumerates the three signal dimensions. No filler or repetition. It could be slightly clearer with a verb, but it 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?

For a read-only, single-parameter, no-output-schema tool, the description gives the essential domain and dimensions. However, it omits what the output shape is (numeric concentration, categorical reliance?), any limitations (coverage of minerals, time lag), and when to prefer it over other signals. With annotations covering safety and schema covering the parameter, this is minimally sufficient but leaves gaps an agent might need for confident use.

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% with a single documented parameter that includes examples (lithium, cobalt, gallium). The description does not expand on parameter meaning beyond the schema, but with full schema coverage and one simple string parameter, the 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 specifies the verb-less signal but clearly identifies the resource: 'critical-minerals supply signal for a commodity' and lists the dimensions returned (supply concentration, import reliance, refined vs mined read). It distinguishes the tool from the thematic siblings (equity_signal, labor_pulse, smart_money, token_scan, wallet_pnl) via the commodity domain, but does not explicitly name a contrasting alternative. This is clear but stops short of full sibling differentiation.

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?

No when-to-use or when-not-to-use guidance is provided. The description mentions it is free USGS/public data, which implies it is a reference signal, but it does not advise when an agent should call this instead of other market or supply tools. The sibling tools are from unrelated domains, so context is inferable but not explicit.

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 the safety profile is fully covered. The description adds the output shape (signal + percent upside) and the input sources, which is useful, but it says nothing about freshness, caching, or what happens for tickers with no coverage (a real risk given openWorldHint).

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?

Single, front-loaded sentence with no filler. Every clause carries information: domain, output fields, and data sources.

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-param read-only tool with a 100% covered schema, the description is nearly sufficient. The main gap is that openWorldHint=true implies coverage variability (missing tickers, non-US tickers, stale consensus), and the description gives no guidance on those edge cases or the format of 'percent upside'.

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 single parameter is already fully documented including format example (AAPL) and length bounds. With only one parameter and no ambiguity, this is a solid baseline; the description adds little beyond confirming 'ticker' is a US equity symbol, but nothing is missing.

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 combination: produces a buy/neutral/sell signal and percent upside to analyst price target for a US equity ticker. Sibling tools (critical_minerals, labor_pulse, wallet_pnl, token_scan) operate in entirely different domains, so differentiation isn't a concern here, though the description doesn't position itself against anything.

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 phrase 'from fundamentals + consensus' implies the methodology and thus when it applies (equity analysis grounded in analyst data), but there is no explicit when-to-use, when-not-to-use, or alternative routing. Adequate but leaves context inference to the agent.

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 useful provenance ('BLS data'), implying an authoritative external source and a monthly cadence, but says nothing about data lag, refresh timing, or return format. With annotations carrying the behavioral burden, this is a modest but real addition.

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 lists the payload first and the source last. Every clause earns its place by naming a distinct metric; there is no 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 zero-parameter read with no output schema, the description effectively enumerates the metrics the caller will receive, which compensates for the absent output schema. Annotations cover the safety profile. Only minor gaps remain (refresh cadence, units/seasons), so it is nearly 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?

The tool takes zero parameters, so the baseline is 4, and schema coverage is 100% with an empty properties object. Nothing about argument semantics is left for the description to clarify.

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 the exact resource (the US labor market) and enumerates the precise signals returned – nonfarm payrolls, unemployment rate, wage growth, JOLTS openings/quits, and participation. An agent can tell it apart from the finance/crypto siblings (equity_signal, smart_money, token_scan) purely by domain. It lacks a leading verb like 'retrieve', but the resource and contents are unambiguous.

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 when-to-use guidance, no statement of prerequisites, freshness, or the conditions that would select this over a sibling. The 'signal' framing implies retrieval for macro analysis, but that is inference, 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description usefully discloses data provenance (SEC filings, congressional disclosures, 13F) which annotations cannot convey, but says nothing about data freshness, latency, or how sources are weighted when they conflict.

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 dense sentence that front-loads the tool's identity and then lists the aggregated sources and the output. No filler and no redundancy.

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 read-only computed signal with no output schema, the description conveys both the inputs and the return shape (accumulation/distribution signal + conviction). Missing only edge-case behavior, e.g. what happens for non-US or thinly covered tickers.

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 ticker parameter is fully documented in the schema, so the description need not repeat it. It adds no format or constraint detail beyond what the schema already provides, which matches the baseline 3.

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 ('Composite smart-money signal for a US stock') and enumerates the exact inputs aggregated (Form-4 insider buys, congressional trades, 13F flow, analyst consensus) plus the output shape. It is clear on its own, but gives no signal about how it differs from the sibling 'equity_signal', which sounds adjacent.

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 when-to-use guidance, no prerequisites, and no mention of any alternative sibling tool. The agent must infer the use case entirely from the description's content.

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 fully covered without the description. The description adds that a report is returned in a 'signal-first' shape and that multi-chain coverage exists, but says nothing about latency, cost, rate limits, or what the report actually contains beyond the listed signals.

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 dense sentence front-loads the domain, then the returned signals, then the supported chains. No filler, no restatement of the title, 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?

For a two-parameter read-only scanner with a fully documented schema, the description covers what is scanned, on which chains, and the general shape of the return ('signal-first report'). It is nearly complete; a brief note on the risk-score scale or what 'signal-first' means 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 100%, with both the chain enum and the address format already documented in the schema. The description's 'EVM or Solana token' phrasing reinforces the address-format duality but adds no syntax or default-value detail beyond what the schema provides, 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 verb and resource ('Crypto token due-diligence') and enumerates the exact risk dimensions covered: honeypot/rug risk score, ownership, liquidity, and holder concentration. It also names the supported token universes (EVM or Solana), so an agent can distinguish it from unrelated siblings like wallet_pnl or smart_money at a glance.

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?

'Due-diligence' implies the context of use (vetting a token before interacting with it), but there is no explicit when-to-use/when-not-to-use guidance and no alternative tool is named. Usage is inferable from the purpose rather than stated, which lands at the minimum-viable level.

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 without the description. The description adds only that both realized and unrealized PnL are returned alongside trade history, which is useful scope information but discloses nothing about rate limits, address validity, empty-history behavior, or how unrealized PnL is computed.

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 tight sentence with no filler, and the core resource (PnL) is front-loaded ahead of the scoping qualifiers. It is appropriately sized for a two-parameter read 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?

With no output schema, the description carries more of the return-value burden, and it only gestures at the payload ('realized/unrealized P&L and trade history') without indicating structure, per-trade granularity, or denomination/currency. Annotations do cover the mutation profile, and the parameter schema is complete, so the remaining gap is moderate rather than severe.

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%: the schema already documents 'wallet' as a Base address (0x…) and 'days' as a 1-365 lookback with default 30. The description's mention of 'Base wallet address' and 'lookback window' only restates the schema, adding no format, validation, or edge-case detail.

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 verb+resource pair: realized/unrealized PnL plus trade history, scoped to a Base wallet address and a lookback window. That is enough for an agent to identify it apart from the sibling tools (critical_minerals, equity_signal, labor_pulse, smart_money, token_scan), though it never explicitly contrasts itself with the analytics-adjacent siblings like smart_money or token_scan.

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 when-to-use or when-not-to-use guidance, no prerequisites, and no named alternative. The lookback-window phrasing implies a time-scoped query, but an agent gets no criteria for choosing this tool over smart_money or token_scan when answering a wallet question.

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