Intercom

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

The description clearly states that the tool picks the right tool and fills arguments, indicating autonomous behavior. No annotations are provided, so the description carries full burden. It does not disclose potential limitations (e.g., if it can fail, if it requires certain permissions, or if it makes external API calls). However, the description is upfront about its general purpose and does not contradict any 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 concise (three sentences) and front-loaded with the core purpose. Every sentence adds value: the first states the action, the second explains the mechanism, the third provides concrete examples. No wasted words.

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 simplicity (one parameter, no output schema, no annotations), the description is complete enough for an agent to use it correctly. It covers purpose, usage, and examples. The only minor gap is that it doesn't specify the format or reliability of the answer, but this is acceptable for a general-purpose query 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% for the single parameter 'question', with a clear description in the schema. The description adds meaning by explaining the parameter's role in natural language and providing examples. The description effectively adds value beyond the schema by illustrating usage scenarios.

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 takes a natural language question and returns an answer from the best data source. It distinguishes itself from other tools on the server (e.g., discover_tools, ic_get_contact) by explicitly saying it picks the right tool and fills arguments, making it a general-purpose query tool rather than a specific data accessor.

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 provides explicit when-to-use guidance: 'just describe what you need' and gives examples of appropriate questions. It implies when not to use it (e.g., if you need to browse tools or learn schemas, you don't need to; this tool does it for you). The alternative is to use other tools directly, but the description positions this as the simpler option.

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 and destructiveHint. The description adds beyond annotations by detailing the tool's process (resolves market, classifies bet, fans out to packs, returns evidence packet + comparison). It also reveals that it is a 'core demo product' and that it auto-selects data packs based on bet type.

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 that is front-loaded with the core purpose. Each sentence adds value, explaining inputs, process, output, and use cases. Though slightly lengthy, it contains no filler and is well-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?

For a tool with 2 parameters, no output schema, and existing annotations, the description covers all essential aspects: what it does, acceptable inputs, internal logic (fan-out), and output form (evidence packet + comparison). It does not detail the exact structure of the evidence packet, but the provided information is sufficient for an agent 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?

Schema coverage is 100% and already includes detailed descriptions for both parameters (depth enum with meanings, market input types). The tool description adds minor context (e.g., 'quick = 2-3 evidence sources') but largely restates what the schema provides. 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 clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It specifies verbs (pull, resolve, classify, fan out) and the resource (Pipeworx data for Polymarket bets). It distinguishes from siblings by focusing specifically on betting research, contrasting with general tools like ask_pipeworx.

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: 'Use for "should I bet on X?", "what does the data say about this Polymarket market?", or "is there edge in this bet?"' It also implies superiority over alternative approaches: 'agents that get bet-relevant context here convert better than ones that have to discover the packs themselves.'

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 return data per type (revenue, net income, etc. for companies; adverse events, approvals, trials for drugs) and mentions resource URIs. With no annotations, it carries full burden and does well, but lacks details on side effects or permissions.

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: action, type-specific details, efficiency claim. No fluff, front-loaded purpose, 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?

Sufficient for a two-parameter tool with no nested objects; covers input format and output data well. Minor gap: no explicit output structure description, but agents can infer from data fields listed.

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 has 100% coverage, and description adds meaning: explains values format for company (tickers/CIKs) vs drug (names), and enumerates type options. This goes beyond the schema's generic 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?

Description clearly states 'Compare 2–5 entities side by side in one call', specifies two entity types (company/drug) with distinct data fields, and contrasts with sibling tools like resolve_entity by highlighting efficiency gains.

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?

Implicitly guides usage by stating it replaces 8–15 sequential calls, suggesting efficiency for multi-entity comparisons. However, it does not explicitly mention when not to use or alternatives for single entities.

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

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

With no annotations, the description carries the full burden. It discloses that the tool searches and returns tool names and descriptions, and implies it's a read-only search. However, it does not mention any rate limits or caching behavior, which would warrant a 5.

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: the first clearly states the function, the second gives actionable usage guidance. No wasted words.

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 simplicity (2 parameters, no output schema, no nested objects), the description is complete enough. It explains what the tool does, when to use it, and how to use the query parameter. Missing details like default limit or maximum are 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%, so baseline is 3. The description adds a usage example for the query parameter ('analyze housing market trends'), which is helpful but does not provide additional constraints or 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?

The description clearly states the tool searches a tool catalog by natural language query, returns relevant tools, and explicitly says to call it first when many tools are available. This distinguishes it from siblings like ask_pipeworx or recall which serve different purposes.

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 'Call this FIRST when you have 500+ tools available and need to find the right ones for your task.' This provides clear guidance on when to use it versus 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?

With no annotations, the description carries the full burden. It discloses the output format (pipeworx:// URIs), the bundled data sources, and a performance consideration (avoiding slow federal contracts). However, it does not address failure modes, data freshness, or what happens if the entity is not found.

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 highly efficient: a single sentence states the core purpose, followed by a focused list of data sources and key behaviors (URIs, call savings, exception for federal contracts). Every sentence earns its place with 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 the tool's complexity (multi-source aggregation) and the absence of an output schema, the description covers the key return values (citation URIs) and data types. It mentions limitations (only company type, no names) and alternatives. A small gap is the lack of detail on error handling or data completeness, but overall it provides sufficient context for an agent to decide to invoke it.

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

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

The input schema already documents both parameters (type and value) with enums and descriptions, yielding 100% coverage. The description adds value by clarifying that type is currently limited to 'company', and that value accepts ticker or CIK (not names), directing users to resolve_entity first—information not fully captured in 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 clearly states it retrieves a full entity profile, lists the data sources included (SEC filings, XBRL data, patents, news, LEI), and contrasts with usa_recipient_profile. However, it does not explicitly differentiate from sibling tools like compare_entities or resolve_entity, leaving some ambiguity.

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 on when to use (for a comprehensive profile in one call) and when not (for federal contracts, use usa_recipient_profile). It also implies using resolve_entity first if only a name is available, and highlights efficiency gains over 10-15 sequential calls.

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

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

No annotations provided, so description carries full burden. It confirms deletion but does not mention whether deletion is irreversible, if confirmation is needed, or if related data is affected. For a destructive operation, more behavioral context is expected.

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?

Extremely concise: 5 words, no fluff. Every word 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?

Given the tool's simplicity (1 param, no output schema, no annotations), the description is too minimal. It fails to mention deletion consequences, error conditions, or behavior when key does not exist.

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 covers the single parameter with a clear description. The tool description does not add any new info beyond what the schema provides, but with 100% coverage, 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 strong verb (Delete) and specific resource (stored memory by key), clearly distinguishing it from sibling tools like recall (retrieve) and remember (store).

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 vs. other memory tools (e.g., recall for reading, remember for writing). The description implies deletion is for cleanup but does not specify prerequisites or 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. The description only states the basic action and required parameter. It does not mention whether the contact must exist, what happens if not found, authentication requirements, or any side effects. This is a significant gap.

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

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

The description is a single sentence, concise and front-loaded with the essential information. No wasted words.

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 is simple (single required parameter, no output schema), the description is minimally adequate. It states what the tool does and the required parameter. However, it does not describe the output or any potential errors. For a simple getter, this might be acceptable but could be more 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%: the only parameter 'id' is described as 'Contact ID' in the schema. The description does not add extra meaning beyond what the schema provides. Baseline 3 is appropriate since schema does the heavy lifting.

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 specific Intercom contact by ID. The verb 'Get' and resource 'contact' are precise, and it distinguishes itself from sibling tools like ic_search_contacts (which is for searching) and ic_list_companies (different resource).

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 does not explicitly state when to use this tool versus alternatives. However, its purpose is clear and limited to fetching by ID, which implies it is for single-record retrieval. No guidance on when not to use it or mention of alternatives 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?

With no annotations, the description carries the burden. It states it returns 'full message thread,' which is useful, but does not disclose any side effects, rate limits, or error conditions. The behavior is implied as a safe read, but not explicitly stated.

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 sentence is concise and front-loaded with the key action. No unnecessary words. However, it could be slightly improved by adding a brief note about what the response contains.

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 has only one parameter and no output schema, the description provides the essential purpose. However, it lacks details about the response format or any prerequisites, which would be helpful for an agent. It is adequate but not thorough.

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 baseline is 3. The description adds value by stating 'with full message thread,' which implies the output includes messages, not just conversation metadata. This goes beyond the schema's 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?

Description clearly states the tool gets a conversation by ID and includes the full message thread, specifying the resource and scope. However, it does not differentiate from sibling tools like ic_list_conversations, which also return conversations but in a different 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 on when to use this tool vs alternatives (e.g., ic_list_conversations for listing vs getting details). The description implies it's for retrieving a single conversation with messages, but no explicit when/when-not or alternative tools mentioned.

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 are absent, so the description carries the full burden. It only states the basic action without disclosing behavioral traits such as pagination behavior, rate limits, or whether the list is exhaustive. No output schema exists to compensate.

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 conveys the tool's purpose without extraneous text. It could benefit from slightly more detail, but it is concise and 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?

Given the tool's simplicity (list operation with two optional parameters), the description is barely adequate. It lacks details on default behavior (e.g., page size), return format, and potential limitations, making it insufficient for an agent to use confidently without external knowledge.

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% for both parameters (page, per_page), so the baseline is 3. The description adds no additional meaning beyond what the schema already provides, but no further elaboration is necessary given the simple 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?

The description clearly states the action ('List') and the resource ('Intercom companies'), making the purpose immediately understandable. However, it does not differentiate from sibling tools like ic_list_conversations, which is acceptable given the distinct resource name.

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 alternatives. Sibling tools like ic_search_contacts suggest similar functionality for contacts, but no exclusion criteria or context is given.

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 are empty, so description carries full burden. It does not disclose pagination behavior (cursor-based), rate limits, or read-only nature. However, the schema partially fills in pagination details.

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 sentence, no wasted words. Could be slightly improved by including key details like pagination or filtering.

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 no annotations, description should clarify return format, pagination details, and typical use cases. It only states 'List Intercom conversations', which is insufficient for a listing 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 coverage is 100% and already describes parameters. Description adds no additional meaning beyond the schema, so 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?

Description 'List Intercom conversations' uses a clear verb and resource, but is generic and does not distinguish it from siblings like 'ic_get_conversation' or 'ic_list_companies'. It lacks specificity about scope or filtering.

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 vs alternatives like 'ic_get_conversation' for single conversations. No mention of limitations 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?

With no annotations, the description should disclose behavioral traits. It mentions the resource (contacts including users and leads) but does not state whether the search is exact or fuzzy, what fields are searchable beyond the param hint, or any limits/performance traits.

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 concise with no waste. However, it is too short to add significant value, and the single sentence could be slightly more informative without harming 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?

Given only 1 parameter and no output schema, the description is minimally adequate. It explains the tool's scope (users and leads) but lacks details on search behavior, result format, or pagination, leaving gaps for effective 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%, and the description confirms the query parameter can search by email, name, or other field, adding meaningful context 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?

The description states the tool searches Intercom contacts, specifying it includes both users and leads, which clearly identifies the resource and scope.

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 vs. ic_get_contact (which retrieves a specific contact) or other search/list tools. The description lacks any context for selection.

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

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

No annotations are provided, so the description must disclose behavioral traits. It does so by stating the rate limit ('5 messages per identifier per day') and that it is 'Free.' While it does not detail side effects or permissions, for a feedback tool this is sufficient. The description adds value beyond the schema.

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

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

The description is concise and well-structured. It opens with the core purpose, lists use cases, provides guidance, and ends with the rate limit. Every sentence is useful, and there is no redundancy. It is front-loaded with the most important 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 tool has 3 parameters (one with nested object), no output schema, and no annotations, the description covers all necessary aspects: purpose, usage, constraints (rate limit), and tips for effective feedback. It is complete enough for an agent to understand how and when to use 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%, and the parameter descriptions in the schema are detailed (especially for 'type' with enum explanations). The description does not add new information about the parameters beyond what the schema already provides. According to the rubric, a score of 3 is appropriate when schema covers parameters well and description adds no extra semantic value.

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 purpose: 'Send feedback to the Pipeworx team.' It lists specific use cases (bug reports, feature requests, missing data, praise), making it easy for the agent to understand when to use this tool. It distinguishes itself from siblings like ask_pipeworx (which queries data) by being the designated feedback channel.

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 provides explicit usage guidelines: 'Use for bug reports, feature requests, missing data, or praise.' It also advises what to include ('describe what you tried in terms of Pipeworx tools/data') and what to avoid ('do not include the end-user's prompt verbatim'). Additionally, it mentions the rate limit, setting clear expectations for usage.

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 openWorldHint=true. The description adds behavioral context beyond annotations by detailing the two modes, the search across events, and the monotonicity checking logic, which aligns with read-only behavior.

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

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

The description is a single paragraph with clear structure: general purpose, mode explanations, and an example. Every sentence adds value, with no redundancy or wasted words.

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 specifies return format: ranked opportunities with trade direction and reasoning. It sufficiently covers the complexity of two modes and the cross-event search, making it complete for effective 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 descriptions for both parameters. The description enriches meaning by explicitly linking each parameter to a mode and providing examples, especially for the topic parameter, adding value 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 clearly states the tool finds arbitrage opportunities by checking monotonicity violations. It specifies two distinct modes (event and topic) and differentiates itself from siblings by focusing on arbitrage across related markets.

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 provides clear context for when to use each mode: event mode for single-event child markets, topic mode for cross-event arbitrage. It includes an example of cross-event necessity but lacks explicit exclusions or 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=true, and the description adds significant behavioral context: it scans top markets, groups by asset, fetches price history once, computes probabilities per market, and ranks by edge magnitude. It also notes the version (V1) and that it returns a ranked list with trade direction, fully disclosing its operation.

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: the first summarizes the main action, and the second provides detailed context and process. It is concise, front-loaded, and contains no extraneous 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 tool's complexity and the absence of an output schema, the description thoroughly covers the algorithm, inputs (limit, window, min_edge_pp), and return value (ranked list with trade direction). It sets expectations for the agent about how the tool works and what it produces.

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 baseline is 3. The description adds overall algorithm context but does not significantly elaborate on parameter meanings beyond what the schema provides. It explains that 'limit' returns top N edges, 'window' filters by volume window, and 'min_edge_pp' filters by edge size, but these are already in 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 clearly states the tool scans high-volume Polymarket markets, computes model probabilities using Pipeworx data, and returns markets with the largest disagreement (edge), including a suggested trade direction. It specifies the scope (crypto-price bets, lognormal model) and distinguishes it from sibling tools 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 says it is 'built for the what should I bet on today question', providing clear guidance on when to use it. However, it does not mention when not to use it or compare directly with 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?

The description discloses key behavior: if key is omitted, it lists all keys; if key is provided, it retrieves that memory. No annotations exist, so the description carries full burden. It could mention that recall is read-only (no side effects), but the listing behavior is clear.

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, zero waste. The first sentence states functionality; the second provides usage context. Information is 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?

Given no output schema, the description does not detail the return format (e.g., string vs structured data). However, for a simple key-value recall tool, this is acceptable. The description covers purpose, usage, and parameter behavior completely.

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 schema already documents the parameter. The description adds value by explaining the conditional behavior (omit to list). It could be more precise about return format, but the semantics are sufficient.

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 action (retrieve/list) and resource (stored memory) with precise scoping ('by key' vs 'omit key'). It also distinguishes from siblings like 'remember' and 'forget' by specifying retrieval functionality.

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 says when to use the tool: 'Retrieve context you saved earlier...'. It also implies when not to use an alternative (e.g., 'remember' for storing, 'forget' for deleting). The guidance is complete and 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?

With no annotations, the description carries the full burden. It details the parallel fan-out behavior for type=company across three sources, the return structure including URIs, and the accepted date formats. It is transparent but lacks mention of rate limits or authentication.

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, well-structured paragraph of 5 sentences. It is front-loaded with purpose, then provides details. Every sentence is informative with no fluff.

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 complexity (three parallel sources, multiple formats), the description covers the main behavioral aspects, return structure, and parameter guidance. It lacks mention of pagination or limits, but is otherwise 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%, so baseline is 3. The description adds value by explaining the enum for type (only company), giving examples for since ('2026-04-01', '7d', etc.) and recommending '30d' or '1m' for typical monitoring, and clarifying value as ticker or CIK.

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 'what's new about an entity since a given point in time' with specific verbs and resources. It differentiates from siblings like entity_profile and compare_entities by focusing on dynamic changes over time.

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 suggests use cases ('brief me on what happened with X' or change-monitoring workflows) and provides examples. It does not mention when not to use it or alternatives, but the guidance is clear and 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?

With no annotations provided, the description bears full burden. It discloses persistence behavior (authenticated users get persistent memory, anonymous sessions last 24 hours), which is beyond basic tool purpose. It does not mention rate limits or data limits.

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: first defines core function, second gives usage examples, third notes persistence behavior. No redundancy, front-loaded with key action and resource.

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 simple parameters (2 strings) and no output schema, the description is sufficient. It covers purpose, usage, and persistence. Could mention that the value is limited to text or size constraints.

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 parameters described). The description adds context on what types of values to store ('findings, addresses, preferences, notes') and example keys, which supplements the schema's basic type info.

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 stores a key-value pair in session memory, with specific use cases like saving findings, preferences, or context. It distinguishes itself from sibling tools like 'recall' (retrieval) and 'forget' (deletion).

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 explains when to use this tool (save intermediate findings, user preferences, context across calls) and implies not to use it for retrieval (handled by 'recall') or deletion (handled by 'forget'). It lacks explicit when-not-to-use scenarios.

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

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

No annotations provided, so description carries full burden. Indicates a read operation (resolve) and mentions that it replaces multiple calls, adding behavioral context. However, lacks details on error handling, rate limits, or permissions. For a simple lookup tool, this is adequate.

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, front-loaded with core purpose and key details (version, type, example inputs, outputs). No unnecessary words. Efficient and scannable.

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?

Tool complexity is low (2 params, no output schema, no nested objects). Description covers purpose, inputs, outputs, and even versioning (v1). Siblings are mostly contact-related, so this tool stands out. Sufficient for an AI agent to select 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% (both parameters described). Description adds value beyond schema by providing concrete examples (e.g., 'AAPL', '0000320193', 'Apple') and explaining the return format (ticker, CIK, name, URIs), making parameter meaning clearer.

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 it resolves entities to canonical IDs, specifies v1 supports 'company' type, and provides specific example inputs (ticker, CIK, name) and outputs (ticker, CIK, name, URIs). Replaces 2-3 lookups, distinguishing from sibling tools like ic_get_contact which handle contacts.

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 'v1: type="company"' and lists accepted input formats, indicating when to use. Implies it's for company entity resolution, but does not state when not to use or provide alternatives. No sibling tools overlap directly, so context is clear but lacks exclusions.

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

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

No annotations are provided, so the description carries full burden. It discloses the tool returns a verdict, extracted structured form, actual value with citation, and percent delta. It mentions the data source and efficiency gain, but does not address error handling, rate limits, or prerequisites. Transparency is good but not exhaustive.

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 three sentences: first states the core function, second details supported claims and data sources, third lists outputs and efficiency. No redundant words, and key information is 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?

Given the single parameter and lack of output schema, the description adequately explains the tool's behavior: it returns a verdict, structured form, actual value, citation, and percent delta. It also specifies the data sources and scope (public US companies), making the tool's capabilities clear.

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

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

Schema coverage is 100% with a clear description of the 'claim' parameter. The tool description adds context by specifying the domain (company-financial claims for US public companies) beyond the schema example, helping the agent understand valid inputs.

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 fact-checks natural-language claims against authoritative sources, specifically for company-financial claims. It details supported metrics (revenue, net income, cash) and data sources (SEC EDGAR, XBRL), 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 explicitly notes the tool replaces 4–6 sequential agent calls, implying a when-to-use directive. It also specifies v1 supports only company-financial claims for public US companies, providing clear scope but not explicitly listing 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.