Hud

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

The description discloses that the tool internally selects the right tool and fills arguments, abstracting complexity. No annotations are provided, so the description carries full burden. It clearly states behavior: it returns an answer from the best data source without needing to browse tools or schemas.

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, with three sentences plus examples. It front-loads the core purpose and provides useful examples. No unnecessary words, though the examples could be more 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 single parameter and no output schema, the description adequately covers its purpose and behavior. It explains what the tool does internally (routing) and provides examples. For a tool of this complexity, the description is nearly complete; it could mention limitations (e.g., scope of data sources) but is sufficient.

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 value by explaining the question parameter as 'your question or request in natural language,' which aligns with the schema description. With 100% schema description coverage, the baseline is 3. The description does not add further detail beyond examples, but the examples enrich the semantic 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 accepts natural language questions and returns answers, using the best available data source. It distinguishes itself from sibling tools by acting as an intelligent router, unlike specific data lookup tools (e.g., hud_fair_market_rents). Examples make the purpose concrete.

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 advises users to 'just describe what you need' and provides example questions, implying when to use this tool (for any data question in plain English). It does not explicitly state when not to use it or mention alternatives, but the context suggests this is the go-to tool for natural language queries.

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 explains that data for 'company' type comes from SEC EDGAR and for 'drug' type from adverse event/fDA trial counts, and that it returns paired data with URIs. It does not disclose potential side effects (e.g., rate limits, authentication requirements) but these are typical for a read-only comparison tool. Without annotations, the description carries moderate transparency.

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 long, front-loaded with the primary action ('Compare 2–5 entities side by side'), then detailing output per type, and finally a performance claim. It is efficient and well-structured, though slightly more brevity could be achieved.

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 a tool with no output schema, the description adequately explains return values (paired data + URIs). It covers both entity types and their respective fields. However, it does not mention pagination, error behavior, or data recency, which would be useful for a data-rich comparison 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?

The input schema already provides detailed descriptions for both parameters (type enum and values array with examples), achieving 100% schema coverage. The description adds extra context by explaining what fields are compared per type, which complements the schema but does not significantly increase meaning beyond it.

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 verb 'Compare' and the resource '2–5 entities', specifying the two entity types (company, drug) with distinct fields. It distinguishes itself from sibling tools (e.g., HUD tools, memory tools) by focusing on cross-referencing external 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 implies usage for comparing multiple entities ('Compare 2–5 entities side by side') and claims efficiency ('Replaces 8–15 sequential agent calls'). However, it does not explicitly state when not to use it (e.g., for single entities) or provide alternative tools that might be better for other comparison tasks.

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 explains that it returns the most relevant tools with names and descriptions, which is a clear behavioral trait. No annotations are provided, so the description carries the full burden. It could add detail about whether the search is semantic or keyword-based, but it is sufficiently transparent for a search tool.

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

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

The description is three sentences, all front-loaded with the action verb 'Search'. Every sentence adds value: purpose, output, and when to use. No waste.

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 (search, two params, no output schema), the description is complete enough. It explains what the tool does and when to use it. Could mention that it returns results with names and descriptions, which it does. No output schema, so return values are not documented but are implied.

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 has high coverage (100%) with descriptions for both parameters. The description adds context that 'query' should be a natural language description, reinforcing the schema's description. It does not add new semantics beyond the schema, but it aligns well.

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: to search the tool catalog by describing what you need, returning relevant tools with names and descriptions. It uses specific verbs ('search', 'call this first') and distinguishes itself from siblings by being a discovery tool for finding other 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?

The description explicitly tells when to use it: 'Call this FIRST when you have 500+ tools available and need to find the right ones for your task.' This provides clear guidance and context for when it should be invoked, setting it apart from other 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?

No annotations are provided, so the description carries full burden. It describes the data sources and output format (pipeworx:// URIs) but does not explicitly state that the tool is read-only, disclose latency, or mention any side effects. The description is adequate but could be more explicit about behavioral 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 concise (two sentences) and front-loaded with purpose. The first sentence could be slightly more structured, but overall it is efficient and clear.

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 of the tool (aggregating multiple data sources) and the absence of an output schema, the description covers the key aspects: what data is returned, citation URIs, and an alternative for federal contracts. It is sufficiently complete for an agent to understand the tool's scope.

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 adds valuable context: it specifies that the 'type' is currently only 'company', describes valid input formats for 'value' (ticker or zero-padded CIK), and directs users with names to resolve_entity. This goes beyond the schema alone.

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 'Full profile of an entity across every relevant Pipeworx pack in one call,' listing specific data sources and explicitly contrasting with the federal contracts alternative. This differentiates from siblings like compare_entities and resolve_entity.

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 advises when to use this tool (comprehensive profile) and when not to (federal contracts use usa_recipient_profile). It also hints at prerequisites (use resolve_entity if only a name). However, it does not enumerate all sibling alternatives or 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?

The description indicates a destructive action (delete), which is clear. No annotations provided, so the description carries the full burden. It states the operation is irreversible (delete), which is good, but no additional context like whether confirmation is needed or if it's permanent.

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 one short sentence. Every word is necessary, and it's front-loaded with the action and object.

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 delete operation with one parameter and no output schema, the description is nearly complete. It lacks information about return value or confirmation, but for such a simple tool, it's adequate.

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 description coverage is 100% for the single required parameter 'key'. The description adds meaning by specifying it's a 'memory key', which aligns with the schema description. No extra semantic info beyond the schema, but given high coverage, a 4 is appropriate.

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

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

The description uses a specific verb ('Delete') and resource ('stored memory by key'). It clearly states what the tool does. However, it could be more distinctive from siblings like 'recall' or 'remember'.

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

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

The description implies usage when you want to delete a memory by key, but no guidance on when not to use it or alternatives. Given the sibling tools, there's no explicit mention of 'forget' vs 'recall' or 'remember'.

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 the description must disclose behavioral traits. It notes that data is from HUD and focuses on low-income households, but does not mention data limitations, update frequency, or any constraints like rate limits or authentication requirements (beyond the API key parameter).

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, front-loaded with the core action and followed by purpose and usage context. No fluff or redundant 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 no output schema, the description could be more specific about the return format or data structure, but it provides enough context for the agent to understand the tool's purpose and typical use. The input schema is comprehensive, so the description is adequate.

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 all parameters. The description adds context about the data's purpose but does not add semantics beyond the schema for individual parameters. 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 it gets CHAS data from HUD and explains its purpose (demonstrating housing problems and needs, used for planning affordable housing). The verb 'Get' combined with the resource 'Comprehensive Housing Affordability Strategy (CHAS) data' is specific and distinct from sibling tools like hud_fair_market_rents or hud_income_limits.

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

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

The description implies use cases for planning affordable housing, but does not explicitly state when not to use it or suggest alternatives among sibling tools. However, the context of 'communities to plan affordable housing' provides clear 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?

No annotations provided, so description carries full burden. It states the tool 'maps' and is 'essential for geographic analysis', which suggests a read-only operation. However, it does not disclose details like API rate limits, authentication needs (only mentions an API key parameter but not required permissions), or whether the crosswalk data is updated periodically. Adequate but minimal behavioral context.

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

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

Two sentences, no waste. First sentence defines the tool, second sentence gives usage context. Efficient 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 3 simple parameters, 100% schema coverage, no output schema, and no annotations, the description is fairly complete. It explains what the tool does and why it's useful. Could mention that results are typically a list of geographic codes, but not essential.

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 description adds value by explaining the mapping types (e.g., ZIP-to-tract) and providing examples like '90210' and '06037'. This goes beyond the schema's basic parameter 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 that the tool maps between ZIP codes, census tracts, counties, CBSAs, and congressional districts, using a specific verb 'Maps' and resource 'HUD USPS ZIP code crosswalk'. It distinguishes from siblings like hud_chas or hud_fair_market_rents by focusing on geographic crosswalking, but could be more explicit about its unique role.

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. The description implies it's for geographic analysis when joining data from different sources, but does not specify when not to use it or mention sibling 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?

No annotations provided, so description carries full burden. It explains what FMRs are used for but does not disclose any side effects, rate limits, or authentication requirements beyond the API key parameter.

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 concise with three sentences: purpose, context, output. No redundancy, front-loaded with key action.

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, description explains return value (rent estimates by bedroom count). Complexity is moderate, and description covers core functionality adequately.

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 does not add meaning beyond schema; it mentions 'by bedroom count' but that is implicit in output, not 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 tool retrieves Fair Market Rents from HUD and explains their use cases (Housing Choice Voucher, Section 8, HOME). It distinguishes from siblings like hud_income_limits and hud_chas by focusing on rent estimates by bedroom count.

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

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

The description implies usage for obtaining FMR data but lacks explicit guidance on when to use this vs. other HUD tools. No mention of prerequisites (e.g., API key) 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 provided, so description carries full burden. Describes return thresholds but does not disclose pagination, rate limits, or whether the API requires authentication beyond the API key. Does not mention if data is cached or real-time.

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 concise sentences that front-load the purpose. No wasted words, but could be slightly more structured with bullet points for the return values.

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 adequately explains the return thresholds. Tool is simple (4 params, no enums), so description is sufficient for a basic understanding. However, missing details on how output is structured (e.g., by family size) could be improved.

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

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

Schema description coverage is 100%, so the schema documents all parameters well. The description does not add meaning beyond the schema (e.g., no explanation of FIPS codes or metro area codes). 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?

Clearly states it retrieves HUD income limits for housing programs by area, specifying eligibility categories (extremely low, very low, low) and family size. Distinguishes itself from sibling tools like hud_chas and hud_fair_market_rents.

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 implies use for determining income eligibility but does not explicitly state when to use versus alternatives like hud_chas or hud_fair_market_rents. No guidance on when to omit parameters.

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 states the tool lists codes and names, which implies a read-only operation. No annotations are provided, so the description carries the burden. It does not detail any destructive behavior or rate limits, but given the simplicity of the operation, the description 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 with no wasted words. Front-loaded with the primary action and includes the 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?

Given the simple parameter set (one required string), no output schema, and straightforward purpose, the description is complete. It tells the agent what the tool does and why it is useful.

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 one parameter '_apiKey' documented in the schema. The description does not add extra meaning about the parameter beyond the schema, but the schema already fully describes it. 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 lists U.S. state codes and names from the HUD API, with the specific verb 'list' and resource 'state codes and names'. It also distinguishes itself by mentioning its utility for discovering valid state codes for other HUD 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?

The description explains when to use this tool: 'Useful for discovering valid state codes to use with other HUD tools.' It implies a preparatory or lookup context, but does not explicitly mention when not to use it or 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?

No annotations provided, so description handles transparency. Mentions rate limit (5 per day per identifier) and that it's 'Free'. Could add more about side effects but adequate for a feedback tool.

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

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

Four sentences, each with clear purpose: purpose, use cases, instruction, rate limit. No superfluous text. Well-structured 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?

Covers key aspects for a feedback tool: what to send, how to structure, rate limit. Lacks description of outcome (e.g., acknowledgment). But sufficient given simplicity and no 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?

Schema coverage is 100% but description adds value by instructing not to include end-user's prompt verbatim and providing context for the optional context object. Enhances understanding beyond 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 'Send feedback to the Pipeworx team' and lists specific use cases: bug reports, feature requests, missing data, or praise. It distinguishes from sibling tools like ask_pipeworx and discover_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?

Provides explicit guidance on when to use (feedback) and what to include (what you tried, not the user's prompt). Includes rate limit info. Lacks explicit exclusion of alternatives but 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?

No annotations are provided, so the description must disclose behavioral traits. It clearly states the two behaviors (retrieve by key or list all), the persistence across sessions, and implies a storage mechanism. However, it does not mention side effects (e.g., if recall is destructive, if it requires special permissions, or what happens if the key doesn't exist). Still, the description is fairly transparent for a simple read 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 a single, well-structured sentence that front-loads the action ('Retrieve a previously stored memory by key, or list all stored memories') and then provides usage guidance. Every part earns its place 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?

Given the tool's simplicity (single optional parameter, no output schema), the description is complete enough. It covers both modes and mentions cross-session persistence. Minor omission: it doesn't specify what happens if the key does not exist (error vs empty result), but for a simple retrieval tool this is acceptable.

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 has 100% coverage: the only parameter 'key' is described in the schema and the description adds context on when to omit it. The description goes beyond the schema by explaining the dual behavior (retrieve vs list) and the session persistence, which enriches the parameter's meaning.

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 ('retrieve') and resource ('memory by key') and clearly distinguishes the two modes: retrieving a specific key or listing all memories when key is omitted. It also hints at its use across sessions, which differentiates it from other 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?

The description explicitly states when to use this tool ('to retrieve context you saved earlier') and when to omit the key ('to list all stored memories'). It provides clear guidance on both modes, and the context of 'session or previous sessions' helps the agent decide when to use recall versus remember or forget.

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?

Describes parallel fan-out to three sources, return format (structured changes, total_changes count, URIs). Since no annotations are provided, the description carries the full burden. It is transparent about behavior, though it doesn't state whether it's read-only (implied by design).

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

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

One paragraph, front-loaded with purpose, followed by specific details. Every sentence adds value, 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?

Since there is no output schema, the description explains return values (structured changes, count, URIs). It covers all parameters, constraints, and behavior, making it fully informative for an AI 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% (all parameters documented), baseline is 3. The description adds value with details on the `since` parameter (ISO date or relative formats) and notes that `type` is limited to 'company'. This exceeds the schema documentation.

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

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

The description clearly states the tool returns what's new about an entity since a given time, specifying the entity type (company) and the data sources (SEC EDGAR, GDELT, USPTO). This differentiates it from sibling tools like entity_profile or compare_entities.

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 suggests use cases: 'brief me on what happened with X' or change-monitoring workflows. It does not discuss when not to use, but the context is clear.

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 discloses memory persistence behavior (authenticated vs. anonymous) and intended use. Does not mention overwrite behavior or limits, but adds meaningful context beyond 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?

Two concise sentences with clear purpose, usage examples, and persistence details. 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?

For a simple key-value store with no output schema, the description covers purpose, persistence, and typical use. Missing details on overwrite behavior or maximum length, but overall sufficient for agent to use 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%, with descriptions for key and value. The description adds value by providing examples of what keys could be (e.g., 'subject_property'), but does not elaborate on value format beyond 'any text'. Baseline 3 is appropriate as schema already does 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 stores a key-value pair in session memory. It specifies the verb ('store'), resource ('key-value pair'), and context ('session memory'), distinguishing it from recall and forget siblings.

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

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

The description provides explicit use cases ('save intermediate findings, user preferences, or context across tool calls') and distinguishes between authenticated (persistent) and anonymous (24h) sessions. However, it does not explicitly contrast with forget or recall, which are 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?

With no annotations provided, the description carries the full burden. It discloses accepted input formats, return fields (ticker, CIK, name, URIs), and the fact it is a single call. This is sufficient for a read-only resolution tool, though pricing or rate limits are not mentioned.

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 (two sentences plus a bullet) yet packs essential information. It is front-loaded with the core purpose and uses no superfluous 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 lacking an output schema, the description explicitly lists the return fields (ticker, CIK, name, resource URIs). For a simple tool with two parameters and no complex behavior, this is complete and leaves 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% with descriptions, but the description adds value by explaining the enum value 'company' and giving concrete examples for the 'value' parameter (e.g., 'AAPL', '0000320193'), which enhances understanding 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 verb 'Resolve', the resource 'entity', and the outcome 'to canonical IDs'. It provides specific examples (ticker, CIK, name) and distinguishes from siblings by noting it replaces multiple calls, 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 explains when to use the tool (when you need canonical IDs) and highlights efficiency gains (replaces 2–3 lookup calls). However, it does not explicitly state when not to use it or mention alternative tools, which would strengthen guidance.

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

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

No annotations provided, but description fully discloses behavior: returns verdict, structured form, actual value with citation, and percent delta. Also explains it replaces 4-6 sequential agent calls, setting clear expectations.

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 yet informative. Two sentences: first states main purpose and scope, second details outputs and efficiency gains. No unnecessary 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 one parameter and no output schema, the description thoroughly explains what the tool returns (verdict, structured form, actual value, citation, delta) and its advantage over sequential calls. Complete for an agent to understand usage.

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?

High schema coverage (100%) for the single 'claim' parameter. Description adds value with examples and explains the natural-language nature, going beyond the schema's basic 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?

Clear verb 'fact-check' with specific resource 'natural-language claim against authoritative sources'. Explicitly limits scope to company-financial claims for US public companies via SEC EDGAR + XBRL, differentiating it from sibling tools.

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

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

States when to use (fact-checking claims, especially financial) and what it covers. Lacks explicit 'when not to use' but the scope is clearly defined, implying alternatives for non-financial claims.

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