SwogeAgentic

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

Annotations already mark this as read-only and open-world. The description adds valuable behavioral context beyond annotations: it chains sibling tools, incurs real cost with a quoted maximum, has a 10-60 second latency, and returns numbers with sources. This helps the agent set expectations and does not contradict the readOnlyHint.

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 deliver the purpose, mechanism, output format, billing model, and latency with no fluff. The key action is front-loaded, and every clause earns its place. This is exemplary conciseness.

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 delegation tool with no output schema, the description covers the essentials: what the agent does, what it returns, how long it takes, and how it is billed. However, it could be more explicit about the types of tasks suited for this tool versus direct sibling use, which is only implied. Overall, it is reasonably 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 description coverage is 100%, and each parameter (task, model, quote) already has a semantic description. The tool description does not add any parameter-specific detail beyond the schema, so the baseline score of 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 action ('Give a whole task to SwogeAgentic'), identifies SwogeAgentic as a Claude agent that chains the tools above, and specifies the output format ('answers with the numbers it read, with sources'). It differentiates itself from the sibling tools by being a higher-level orchestrator, though it doesn't explicitly name a contrasting sibling.

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 'Give a whole task' implies this is for compound research/execution rather than a single tool lookup, and 'chains the tools above' suggests using it when multiple sibling tools are needed. However, it never explicitly states when not to use it or names alternatives, leaving the routing decision 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 and openWorldHint=true, covering the read-only nature. The description adds valuable context by explaining what data is returned (positions, trades, mirror record, ledger) and that it is a paper-trading colony, which informs the agent of the data's nature (simulated, not real-money). This goes beyond the annotations without contradicting them, adding useful behavioral context.

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

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

The description is a single sentence that efficiently packs the core purpose and the optional filter. It is front-loaded with the primary content (what the colony is doing) and includes the filter mention at the end. There is no redundancy or filler, though the opening 'What the ... is doing:' is slightly verbose but not detrimental.

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 summary tool with no output schema, the description sufficiently covers what the agent needs to know: it returns colony activity details and can be filtered. It does not specify the exact response format, but given the tool's simple nature and the annotations covering safety, the description is complete enough for correct invocation. A slight gap is the lack of mention of the quote parameter's purpose in the description, but that is already in the schema.

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 parameters (quote and token) well-described in the schema. The tool description adds minimal value: it reiterates the optional filter on token but does not introduce new syntax or format details. Since the schema already fully documents the parameters, a baseline score 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 states the resource (the SWOGE AI colony) and the specific data it exposes: open positions, buys/sells with results, mirror record, and paper ledger. It distinguishes itself from siblings like scan_token or wallet_intel by focusing on colony-level activity rather than individual token or wallet analysis. The optional filter is also mentioned, making the purpose 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?

The description implies usage (query colony activity) but does not explicitly state when to prefer this over alternatives or mention any exclusions. It lacks guidance like 'use this to see the colony's overall performance' or 'for individual token analysis, use scan_token instead.' The context is clear, but the when-to-use versus not-use 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 declare readOnlyHint=true, but the description says the tool creates an image and may be billed at real cost or charged a fixed per-request price. This directly contradicts the read-only annotation because invoking the tool causes a paid, side-effecting action.

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 four sentences and front-loads the core action before adding billing and output details. Each sentence contributes a distinct fact, though the billing phrasing ('quoted maximum'/'quoted in the 402') is somewhat cryptic and could be tightened.

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 explains billing modes, the SWOGE behavior, and that the return value is image URLs, which is useful given no output schema. However, it does not clarify what quote=true returns (a price instead of image URLs), and the read-only annotation contradiction leaves callers with inconsistent expectations about side effects.

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?

All 6 parameters are already documented in the schema, so the baseline is 3. The description adds a useful prompt nuance about SWOGE characters but does not add material meaning for count, quality, provider, quote, or aspect_ratio beyond the schema.

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

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

The description uses a specific action and resource ('Create an image') and names the two concrete providers, Grok Imagine and ChatGPT Image. This clearly distinguishes it from sibling tools like generate_video and makes the intended function unmistakable.

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 clear usage context by stating that the tool is for generating images and explains the two billing modes depending on API key presence. It does not explicitly list exclusions or alternatives, but the intended use case is unambiguous.

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?

Annotation Contradiction. The description says the tool creates a video and bills the caller in real money, which is a state-changing side effect, while annotations declare readOnlyHint=true. This directly contradicts the annotation and misleads an agent about side effects.

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 compact, efficient sentences carry the essential information: the operation, billing behavior, failure policy, return value, and polling path. No filler or redundant details.

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?

Covers the critical operational details: return type, asynchronous polling via video_status, and cost behavior on success and failure. The schema handles parameter completeness. The annotation contradiction is a notable coherence gap, but the description itself is nearly complete for invoking the 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 100%, so the schema already documents all parameters including prompt, duration, quality, resolution, aspect_ratio, and quote. The description only restates duration and hints at quote-based pricing, adding no meaningful parameter-level semantics beyond the schema.

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

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

States a specific verb, resource, and scope: 'Create a short video with Grok Imagine (6 or 10 seconds).' It also separates generation from polling by saying the tool returns a video id to check with video_status, which distinguishes it from sibling tools.

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?

Explains the follow-up action explicitly: 'poll it with video_status (free).' It also notes the API-key billing condition. It does not enumerate negative cases or alternatives, but the context is clear enough for an agent to decide when to invoke it.

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 and openWorldHint=true, so the read-only safety is covered. The description adds behavioral detail: it returns both newly found tokens and older watched tokens, includes buy/no-buy reasoning, and provides verdicts. This goes beyond the annotation's minimal safety profile, though it doesn't mention pagination or any edge cases.

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 sentence that front-loads the core purpose ('The newest tokens the SWOGE AI colony just found') and then lists the data fields. It's informative without excessive wordiness, though the sentence is long and could be split for readability.

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 the main content but leaves ambiguity about output structure: does 'limit' apply only to new tokens, or also to older watched tokens? Are older tokens a separate section? Since there's no output schema, the description should clarify the response format and the exact effect of the limit parameter. This gap makes it less than fully 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 100% and both parameters (limit and quote) already have descriptive comments. The tool description adds no extra meaning about the parameters; it only describes the output. Baseline 3 applies because the schema handles parameter documentation.

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 resource (newest tokens on Robinhood Chain found by the SWOGE AI colony) and lists specific data points it provides (pool size, cap, 5-minute move, buy rationale), plus older watched tokens with verdicts. This distinguishes it from siblings like scan_token, which likely targets individual tokens.

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 explicit guidance on when to use this tool versus alternatives. It does not mention any sibling or conditions, leaving the agent to infer that this is for discovering new launches. The description is purely descriptive and lacks any 'use this instead of' context.

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 and openWorldHint=true, so the tool is known to be non-destructive and may return data beyond the described scope. The description adds value by confirming the passive nature of the reconnaissance, which aligns with readOnlyHint, and by disclosing the types of findings returned (DNS, certificates, registration, hosting, exposure) with sources. It also explicitly states that people are not accepted, a behavioral limitation not covered by annotations. No contradiction exists.

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, information-dense sentence that front-loads the core purpose and immediately enumerates accepted target types and output categories. Every clause contributes value—no filler or redundancy. It is appropriately sized and structured for quick agent parsing.

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 reconnaissance tool with no output schema, the description adequately explains what is returned (findings with sources) and what is not accepted. It covers the main use cases and constraints. Minor gaps remain—e.g., whether results are paginated, whether rate limits apply, or what the exact response format looks like—but these are not critical for an agent to invoke the tool correctly given its read-only nature and the existing annotation coverage.

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%—both 'target' and 'quote' are fully described in the schema. The description does not add any additional meaning beyond what the schema already provides for these parameters. It merely repeats the allowed target types. Since the schema carries the full weight, a 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 states the tool performs passive reconnaissance on infrastructure and enumerates the exact accepted target types (domain, IP, URL, AS, CVE). It also specifies the output (DNS, certificates, registration, hosting, exposure findings) and each finding includes its source. This is a specific verb+resource definition that distinguishes itself from siblings like wallet_intel or scan_token by scoping to infrastructure rather than people or tokens.

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 a clear exclusion: people-related entities (emails, usernames, phone numbers, names) are not accepted, which helps an agent avoid misuse. However, it does not explicitly state when to use this tool versus alternatives like web_search or scan_token, nor does it mention any prerequisites or context for choosing it. The guidance is partial—it says what not to input but not when it is the best choice.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true; the description adds meaningful behavioral context by naming the live-data nature, the external sources (DexScreener, GoPlus, SWOGE AI colony), and the conditional Robinhood Chain behavior. It does not mention rate limits or failure modes, but annotations already cover the safety profile.

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 sentence delivers the core action, the exact input, and a structured breakdown of outputs with no filler. The key information is front-loaded and every phrase adds value.

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 tool with no output schema, the description covers the essential input requirements and the categories of returned data, including a conditional edge case. It does not specify return shape or formatting, but an agent has enough to select and invoke the tool correctly.

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

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

Schema description coverage is 100%, with both parameters already well documented. The description reinforces the address format and adds context about what the address is used for, but it does not add meaning beyond the schema for the 'quote' parameter. 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 uses a specific verb ('Read live data on a token') and a clear resource ('by its EVM contract address'), then enumerates the exact data categories returned: market, contract security, and SWOGE AI colony observations. This clearly distinguishes it from sibling tools like web_search or wallet_intel.

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 clear context for when to use the tool: whenever a caller needs live market, security, or AI colony data for a specific EVM token address. It does not explicitly name alternatives or exclusion cases, but the intended use case is strongly implied.

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 and openWorldHint=true, and the description's 'read on-chain' aligns with those without contradiction. It adds the scoping of what is read (supply, burnt, vault, price) but discloses nothing deeper like data freshness, price source, or caching behavior — acceptable given the annotations carry the safety profile.

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 19-word sentence that front-loads the verb and resource before enumerating the return fields. There is zero redundancy, and every word contributes to the tool's meaning.

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 tool with one optional fully-documented parameter and safety covered by annotations, the description is nearly complete — it even lists the returned values despite there being no output schema. Minor gaps like price source or data latency are tolerable at this complexity level.

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 the quote parameter is fully documented in the schema already. The description adds no parameter-level detail, and with the baseline of 3 applying at full coverage, it neither needs to compensate nor exceeds the schema's explanation.

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 — 'read on-chain' the $SWOGE token economy — and enumerates the exact data points returned (total supply, burnt, casino vault, current USD price). This specificity makes it clearly distinguishable from all ten siblings, none of which target $SWOGE economics.

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 implies usage context through its specificity, letting an agent infer 'use this for $SWOGE on-chain token metrics.' However, it never explicitly states when to use this tool versus alternatives like scan_token or wallet_intel, nor does it give any exclusions or 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?

Annotations already mark it read-only, and the description adds useful behavioral details: it reports pending/done/failed statuses and explicitly states failed attempts are not charged. The word 'Free' further clarifies the cost behavior beyond the annotation hints.

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?

One compact sentence conveys the purpose, the possible outcomes, and the cost guarantee. No filler or redundant wording, with the essential action 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 simple status-polling tool with two well-documented parameters and read-only annotations, the description is sufficient. It explains the statuses and the failure/cost behavior, and the schema covers the rest; no output schema is expected given the simple return concept.

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 already describes both parameters thoroughly, including that id comes from generate_video and that quote returns the price without executing. The description adds no extra parameter-level meaning, so 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 uses a specific verb ('Read') and resource ('status of a video you started') and enumerates the possible outcomes: pending, done with URL, failed and not charged. This clearly distinguishes it from generate_video, which creates the video, and from other unrelated 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 clearly implies the tool is used after starting a video generation, and the schema reinforces that the id comes from generate_video. However, it does not explicitly state when not to use it or mention any alternatives.

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

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds valuable behavioral context: the address is never contacted, making this a passive/non-invasive lookup. It also clarifies the data source (launchpads the system indexes and SWOGE AI colony measurements). This goes beyond what annotations alone convey.

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, information-dense sentence with front-loaded scope ('what is known about an EVM wallet address') and a clear passive-safety note at the end. Every clause contributes meaningful content, and 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?

There is no output schema, so the description helpfully enumerates the return categories: launched tokens, deployed tokens, and colony measurements with observation counts. It does not specify the exact response shape or error behavior, but for a simple read-only lookup the listed categories plus the passive guarantee are sufficient for an agent to select and invoke it correctly.

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

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

Schema description coverage is 100%, so both parameters are already documented. The tool description adds no parameter-level detail beyond the schema, particularly nothing about the quote flag. Baseline 3 is appropriate because the schema carries the semantic burden.

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 (an EVM wallet address) and the specific information returned: launchpad launches, deployed tokens, and SWOGE colony observations with counts. It does not use an imperative verb, but 'What is known about...' is an effective purpose statement. It doesn't explicitly distinguish itself from siblings like osint_lookup, but the content scope is specific enough.

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 implies the tool is for wallet intelligence queries and notes it is passive, which helps set expectations. However, it gives no explicit guidance on when to prefer this tool over siblings such as osint_lookup or scan_token, and it provides no exclusions or alternative conditions.

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 carry readOnlyHint=true and openWorldHint=true, and the description adds behavioral context beyond that: it reveals the tool is backed by Perplexity, returns ranked results, and includes an extract. There is no contradiction.

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 two sentences with no filler; it front-loads the action, then the return format, then the usage guidance. 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 simple two-parameter search tool, the description covers the tool's function, output fields, and the main use case. While it doesn't mention result limits or error cases, that detail is not required for an agent to confidently select and invoke the 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 100%, so the parameters are fully documented in the input schema. The tool-level description adds no extra parameter semantics, keeping this at 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?

Description uses a specific verb ('Search') and resource ('the web (Perplexity)') and immediately states the return shape (ranked results with title, URL, date, extract). It distinguishes itself from SWOGE-internal siblings by naming external use cases, so an agent can separate it from tools like osint_lookup or swoge_economy.

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 explicitly states when to use the tool: 'Use it for news, projects, people, anything outside SWOGE data.' It provides clear context but stops short of naming alternative tools or giving an explicit when-not-to-use instruction, so it earns a 4 rather than a 5.

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