Nist Beacon

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

Description adds significant context beyond annotations (readOnlyHint, openWorldHint, destructiveHint): explains routing among 2,520 tools, argument filling, and citation URIs. No contradiction with annotations; all behavioral traits are transparently disclosed.

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

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

Front-loaded with key instruction 'PREFER OVER WEB SEARCH', then lists domains and examples. Slightly long but all sentences add value. Efficiently structured.

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 the tool's complexity (routing to 2,520 sub-tools) and the fact that there is no output schema, the description covers purpose, usage, and outcome (structured answer with citations). Could detail output format more, but adequate for the context signals.

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

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

Only one parameter 'question' with schema coverage 100% (schema says 'Your question or request in natural language'). Description adds usage examples but no new semantic detail about the parameter itself. 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?

Description clearly defines the tool's purpose as a meta-routing tool for factual structured data queries, explicitly distinguishing it from web search and listing specific domains (SEC, FDA, FRED, etc.) with concrete examples. This is a specific verb+resource with clear 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?

Provides explicit guidance to prefer this tool over web search for structured data queries, lists triggers like 'what is', 'look up', 'find', etc., and includes examples. While it does not explicitly list when not to use, the positive guidance is strong and effectively steers 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?

The description provides extensive behavioral context beyond annotations: it resolves the market, classifies the bet, fans out to packs based on bet type, returns an evidence packet and market-vs-model comparison, and explains the depth parameter's effect. This fully discloses the tool's internal process without contradicting 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?

The description is front-loaded with the main purpose and includes concrete examples. While effectively packed with information, it is slightly lengthy; a minor trim could improve conciseness without losing 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?

Given no output schema, the description covers the tool's input, internal logic, and output types (evidence packet, market-vs-model comparison). However, it could be more specific about the evidence packet's structure or fields, leaving some ambiguity for the 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% with descriptions for both parameters. The description adds value by specifying that 'quick' means 2-3 evidence sources and 'thorough' is default full fan-out, which is more detailed than the schema enum. It also reinforces the market parameter's accepted formats.

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 researches Polymarket bets by pulling Pipeworx data, resolving the market, classifying the bet, and fanning out to relevant packs. It distinguishes itself from siblings as the core demo product for bet research, making it the go-to tool for this specific use case.

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 lists use cases like 'should I bet on X?' and mentions that agents using this tool convert better than those using packs individually. However, it does not explicitly exclude scenarios or compare with specific sibling tools like ask_pipeworx, missing a clear when-not-to-use directive.

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 indicate a read-only, non-destructive operation, but the description adds no additional behavioral context such as return format or potential limitations.

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 only two words, which is under-specified. Conciseness should not come at the cost of missing essential 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?

Given the simple input schema and lack of output schema, the description should provide more context about what metadata is returned and how it relates to sibling tools.

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% and the description fails to explain the 'chain_id' parameter's meaning or format, leaving the agent with no extra semantic guidance.

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 'Chain metadata' is vague; it lacks a verb and does not clarify what kind of chain or what metadata is returned. It does not distinguish from siblings like 'latest_in_chain' or 'pulse_at'.

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 guidance on when to use this tool versus alternatives. Sibling tools exist for similar chain-related queries but no usage context is provided.

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 indicate a safe, read-only operation. The description adds data sources (SEC EDGAR/XBRL for companies, FAERS for drugs) and mentions it replaces 8-15 sequential calls. No contradiction with 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?

Two sentences with the purpose first, followed by detailed examples. The second sentence is long but packs useful information without 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?

No output schema, but the description lists the specific data fields returned for each type (revenue, net income, etc.) and mentions citation URIs. It could be clearer on the exact return format, but it's mostly 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% with descriptions. The description adds value by explaining how to set 'type' (company/drug) and what to pass in 'values' (tickers for company, drug names for drug), beyond the schema's enum and array descriptions.

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 tool compares 2–5 companies or drugs side by side, using a specific verb ('compare') and resource ('entities'). It distinguishes from siblings by focusing on multi-entity comparison, unlike entity_profile or validate_claim.

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 lists user utterances that trigger use ('compare X and Y', 'X vs Y', etc.) and gives examples for both types. It implies when not to use (single entity) but does not name alternative tools.

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?

Description explains that the tool is a read-only discovery operation, returning 'top-N most relevant tools with names + descriptions'. This aligns with annotations (readOnlyHint=true) and adds behavioral context about return format and 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?

Description is short, front-loaded with the primary purpose, and every sentence adds value. No redundant or unnecessary 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?

Given no output schema and simple parameters, the description fully explains the tool's behavior and context. It covers what it does, when to use it, and what to expect in return.

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?

Input schema already describes both parameters with 100% coverage. The description adds value by explaining that 'query' is a natural language description of data or task and that 'limit' controls the top-N results, though schema already covers this.

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 clearly states the tool 'Finds tools by describing the data or task' and distinguishes it from sibling tools by advising to call it first when many tools are available. It lists specific domains and explains the return of top-N relevant 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?

Description provides clear usage context: 'Use when you need to browse, search, look up, or discover what tools exist' and 'Call this FIRST when you have many tools available'. It does not explicitly state when not to use, but the guidance is actionable.

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 indicate readOnlyHint=true and destructiveHint=false, so the description's disclosure of reading operations is consistent. The description adds valuable behavioral context: it returns a compilation of data from multiple sources (SEC filings, financials, patents, news, LEI) with pipeworx:// citation URIs. It doesn't contradict 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?

The description is front-loaded with the key purpose, then expands with usage cues and return details. It is informative without being verbose, though it could be slightly more concise by grouping related information. The structure logically flows from purpose to usage to outputs.

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 the tool's complexity (aggregating multiple data sources) and no output schema, the description adequately outlines the return types (SEC filings, financials, patents, news, LEI) and mentions citation URIs. It covers the main expectations, though it could mention potential limitations like pagination or size.

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%, but the description enhances parameter meaning beyond the schema. It explains that type is restricted to 'company' for now, and value expects a ticker or zero-padded CIK, explicitly noting that names are not supported and advising to use resolve_entity otherwise. This adds practical usage context.

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's purpose: 'Get everything about a company in one call.' It specifies the verb (Get), resource (company profile), and scope (everything). It differentiates from siblings by noting it aggregates data from multiple tools (SEC EDGAR, USPTO, etc.), making its unique value obvious.

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 lists when to use the tool via example user queries ('tell me about X', 'give me a profile of Acme') and mentions an alternative: if only a name is available, use resolve_entity first. It also states that only ticker or CIK are accepted, not names, providing clear guidance on input requirements.

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 indicate destructiveHint=true. Description aligns with 'Delete' but adds no extra behavioral details (e.g., irreversibility or confirmation). Adequate given annotation coverage.

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: first states action, second provides usage guidance. No wasted words, front-loaded with clarity.

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 single-parameter destructive tool with full schema, the description covers purpose and usage. Could mention key-not-found behavior but not essential without output 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?

Input schema already describes 'key' as 'Memory key to delete' with 100% coverage. Description only repeats 'by key', adding no new meaning. 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?

Clearly states 'Delete a previously stored memory by key.' The verb 'delete' and resource 'memory' are specific. Distinguishes from siblings 'remember' and 'recall' by implication.

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 says when to use: 'context is stale, the task is done, or you want to clear sensitive data.' Also advises pairing with 'remember' and 'recall'.

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 state readOnlyHint=true and destructiveHint=false, so the description adds nothing beyond that. It doesn't disclose what happens if no pulse exists or any other behavioral details. Since annotations cover the main safety profile, a 3 is appropriate.

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 phrase, extremely concise and front-loaded. However, it omits necessary context, so it's not earning its place fully.

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 parameters, no output schema, and simple functionality, the description should still clarify what a 'pulse' is and what the output format looks like. The current text is too vague for an agent unfamiliar with the domain.

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 are no parameters, and schema coverage is 100%. The description implies no inputs are needed, which matches the schema. Baseline 4 for zero-parameter tools.

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 'Most recent pulse' clearly indicates the tool returns a single pulse that is the latest. It distinguishes from siblings like 'pulse_at' (specific time) and 'pulse_by_chain_pulse' (by chain). However, the term 'pulse' is undefined, relying on domain context.

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 guidance is provided on when to use this tool versus siblings like 'latest_in_chain' or 'pulse_at'. The agent has no information about trade-offs or prerequisites.

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 indicate a non-destructive read operation, but the description adds no additional behavioral context such as caching, ordering, or error handling.

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?

Excessively brief; while concise, it sacrifices meaningful content. The single sentence offers minimal value beyond the tool name.

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 tool with one required parameter and no output schema, the description should clarify what a 'pulse' is and what the return value contains. It fails to do so.

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%. The description does not explain what 'chain_id' represents, acceptable values, or how it affects the result.

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 is essentially a tautology of the tool name. It says 'Latest pulse in chain' but does not explain what a 'pulse' or 'chain' is, nor does it distinguish from siblings like 'last_pulse' or 'pulse_by_chain_pulse'.

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 guidance on when to use this tool versus alternatives, nor any indication of appropriate use cases or limitations.

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?

Discloses rate limit (5 per identifier per day), cost (free), quota impact (doesn't count against tool-call quota), and how feedback is used (digests, roadmap impact). Complements annotations (no contradictions).

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 paragraph but well-organized, front-loading purpose. Could be slightly more structured, but every sentence serves a purpose.

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 all necessary aspects: purpose, when to use, parameter descriptions via schema, constraints (rate limit, free), and impact. No additional output schema needed.

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 baseline is 3. Description adds value by explaining the meaning and context of each feedback type beyond the schema's enum descriptions.

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's purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It lists specific feedback categories and distinguishes itself from sibling tools which are data retrieval or analysis 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?

Explicitly details when to use each feedback type (bug, feature, data_gap, praise) and what to avoid (don't paste end-user prompt). Also mentions rate limits and free usage, providing comprehensive usage 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 indicate read-only and non-destructive behavior. The description adds behavioral context: the tool searches, groups markets, checks monotonicity, and returns ranked opportunities with reasoning. It also clarifies that cross-event mode catches cases single-event misses, providing transparency beyond 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?

The description is well-structured with a clear purpose statement followed by mode details. It is concise (two paragraphs) and front-loaded with the key information. Every sentence 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?

Despite no output schema, the description explains what the tool returns (ranked opportunities with trade direction and reasoning). For a complex tool with two modes and cross-event logic, the description is thorough and leaves little ambiguity.

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 covers both parameters with descriptions. The description adds value by explaining the two modes ('event' vs 'topic') and how they map to parameters, including example values. This goes slightly beyond the schema alone, earning a 4.

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 finds arbitrage opportunities on Polymarket by checking monotonicity violations. It distinguishes two modes ('event' and 'topic') with concrete examples, making the purpose specific and distinct from siblings like 'polymarket_edges'.

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?

Explicit guidance is given for when to use each mode: 'event' for a single event slug, 'topic' for cross-event searches. The description explains why cross-event mode is necessary for certain cases, effectively helping the agent select the right mode.

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. The description adds valuable behavioral context: it scans top markets, groups by asset, fetches price history once, and computes model probability. This goes beyond annotations by explaining the internal workflow.

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 approximately 100 words and front-loaded with the core action. Every sentence contributes useful information, though minor redundancy exists (e.g., 'top markets' repeated). Still, it is efficient for an AI agent.

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 mentions it returns 'top N ranked by edge magnitude with suggested trade direction.' This is adequate but lacks specifics on data format (e.g., how edge is represented). For a tool with good annotations, it is sufficient but not exhaustive.

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 description adds meaning to parameters (e.g., 'top N', 'volume window', 'minimum absolute edge'). It explains how the tool groups by asset, which contextualizes the 'window' parameter, enhancing understanding.

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 scans Polymarket markets, identifies where Pipeworx data disagrees with market price, and returns ranked edges. It specifies the coverage (crypto-price bets), the model used, and the output format, distinguishing it from siblings like polymarket_arbitrage.

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 frames the tool for the 'what should I bet on today' question, indicating its primary use case. It implies when to use it over manual browsing, but does not explicitly contrast with sibling tools, though the context is sufficient.

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 indicate readOnlyHint=true and destructiveHint=false, which partially informs behavior. However, the description adds minimal value beyond stating the time unit. It does not disclose what the tool returns, any side effects, or the meaning of 'pulse'.

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 short but at the cost of clarity. It lacks essential details, resulting in under-specification rather than effective 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?

The tool has a single parameter, no output schema, and a minimal description. It fails to explain core functionality or return value, leaving the agent unable to use 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?

The description adds unit context ('epoch ms') for the single parameter 'time_ms'. Given 0% schema description coverage, this is helpful but still insufficient. No explanation of the parameter's role (e.g., query time vs. set time) is provided.

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 'Pulse at UTC time (epoch ms)' is vague. It specifies the time unit but does not explain what 'pulse' means or how it relates to the tool's purpose. It fails to distinguish from sibling tools like 'last_pulse' or 'pulse_by_chain_pulse'.

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 usage guidelines provided. The description does not indicate when to use this tool versus alternatives, nor does it mention any prerequisites or 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, destructiveHint=false, openWorldHint=true. The description adds no behavioral information beyond the annotations, missing opportunities to explain data format, pagination, or availability constraints.

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?

While extremely short, the description is too terse to be useful. It lacks key information and structure, making it more incomplete than concise.

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?

Without an output schema or parameter descriptions, the description fails to explain what the tool returns or how it differs from similar tools. The agent cannot determine if this retrieves a single pulse, a range, or metadata.

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%. The description does not define what 'chain_id' or 'pulse_id' represent, leaving the agent with no semantic understanding of these required parameters.

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 'Pulse by chain + pulse index' essentially restates the tool name and parameter structure without clarifying the actual operation. It fails to specify what a 'pulse' is or what action the tool performs, leaving the agent 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?

No guidance on when to use this tool versus siblings like 'pulse_at' or 'last_pulse'. The description provides no context for selection based on use case or data scope.

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?

Adds behavioral context beyond annotations, such as scoping to an identifier and pairing with other tools, and does not contradict the readOnlyHint and destructiveHint 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?

Four efficient sentences, no wasted words. Each sentence serves a purpose: purpose, usage, scope, pairing.

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?

Adequate for a simple tool with one optional parameter and no output schema. Covers retrieval, listing, scoping, and pairing. Could mention return format but not necessary.

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

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

With 100% schema coverage, the description adds value by explaining the listing behavior when `key` is omitted, which complements the schema's parameter description.

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 retrieves a value by key or lists all keys, distinguishing it from sibling tools like `remember` and `forget`.

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 explains when to use the tool ('look up context stored earlier') and how it pairs with `remember` and `forget`, but does not explicitly list alternatives or when not to use.

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 indicate read-only, open-world, and non-destructive behavior. The description adds significant context: parallel queries to three sources, accepted date formats, and return structure (changes, count, URIs). This extends 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?

The description is concise (5 sentences) and each sentence adds value: purpose, usage, sources, parameter formats, and return structure. It could be slightly more front-loaded, but it is well-structured for an agent.

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 no output schema, the description provides a reasonable overview of return values (structured changes, count, URIs). The tool is moderately complex with three parameters and multiple data sources. The description covers purpose, usage, parameters, and behavior, leaving only detailed output structure unclear.

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?

Input schema has 100% coverage with descriptions for all three parameters. The description adds practical guidance: 'type' is only 'company', 'since' format details (ISO date or shorthand like '7d'), and 'value' examples (ticker or CIK). The description also suggests a default for monitoring ('30d' or '1m').

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's purpose: retrieving recent changes for a company. It uses specific verbs ('What's new with a company') and resources ('company'), and distinguishes from sibling tools by focusing on recent changes across multiple data sources.

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 provides usage guidance with examples like 'what's happening with X?' and 'news on Apple this month'. It explains the fan-out to specific sources (SEC, GDELT, USPTO). However, it does not explicitly mention when not to use this tool or compare to alternatives among 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 indicate non-read-only and non-destructive behavior. The description adds critical context: key-value pairs are scoped by identifier, authenticated users get persistent memory, anonymous sessions retain for 24 hours. No contradictions with annotations; description enriches understanding beyond structured fields.

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

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

The description is a single paragraph but contains all necessary information without redundancy. It is front-loaded with the core action and usage guidance, then adds behavioral details. Slightly longer than ideal but still efficient for the complexity; no wasted sentences.

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 storage tool with no output schema and strong parameter schema coverage, the description provides complete context: purpose, when to use, persistence behavior, and related tools. No gaps remain for the agent to understand how and why to invoke this 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?

Input schema covers 100% of parameters with descriptions. The description adds value by providing example keys ('subject_property', 'target_ticker') and explaining the purpose of the value ('findings, addresses, preferences, notes'), which goes beyond the schema's generic 'Value to store'.

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 ('Save data') and clearly states the resource ('data the agent will need to reuse later'). It distinguishes the tool's purpose from siblings by mentioning pairing with recall and forget, and provides examples of usage like 'resolved ticker' or 'user preference'.

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 ('when you discover something worth carrying forward') and why ('so you don't have to look it up again'). It also references internal siblings 'recall' and 'forget' for complementary operations, offering clear guidance on 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 indicate read-only, non-destructive, open-world behavior. Description adds that the tool returns IDs plus pipeworx:// citation URIs and replaces multiple lookups. This is valuable context beyond annotations, though it doesn't mention potential ambiguity or multiple matches.

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?

Concise at ~90 words, well-structured with purpose, usage, examples, and return info. Every sentence adds value; 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?

Given two simple parameters, full schema coverage, and no output schema, the description adequately covers what the tool does, returns (IDs + citation URIs), and how to use it (before other tools). No critical 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 coverage is 100%, baseline 3. Description adds meaningful examples for the 'value' parameter (e.g., ticker, CIK, name for company; brand/generic for drug), clarifying input formats beyond the schema's generic description.

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 clearly states purpose: look up canonical identifiers (CIK, ticker, RxCUI, LEI) for companies or drugs. Provides concrete examples and distinguishes from sibling tools by focusing on identifier resolution for downstream tool use.

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 states when to use: 'when a user mentions a name and you need the CIK...' and instructs to use BEFORE other tools that need official identifiers. Also notes it replaces 2-3 lookup calls, providing efficiency 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 provide readOnlyHint, openWorldHint, and destructiveHint. The description adds specific behavioral context: returns a verdict with citation and percent delta, and that it replaces multiple steps. No contradictions.

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, each carrying weight: action verb first, usage guidance, then scope/details. Not a word 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?

Despite no output schema, the description explains the return structure (verdict, structured form, actual value with citation, percent delta) and domain limitations. It's complete for an agent to decide and invoke 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 coverage is 100% for the single 'claim' parameter. The description adds meaningful context beyond the schema by providing an example and explaining what the tool returns (verdict types, actual value with citation).

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 'fact-check, verify, validate, or confirm/refute a natural-language factual claim' and explicitly states it handles 'company-financial claims' via SEC EDGAR. It distinguishes from siblings by noting it replaces 4–6 sequential calls.

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 examples of when to use the tool (e.g., 'Is it true that…?') and mentions the domain limitation (v1 supports company-financial claims). While it doesn't explicitly name alternative tools, it frames usage well.

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