Transit Land

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

Describes auto-routing but lacks details on ambiguity resolution, error handling, rate limits, or authentication; with no annotations, more transparency would be beneficial.

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 paragraph with front-loaded purpose and clear usage guidelines; nearly every sentence is informative, though slightly verbose in listing sources.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Lacks return format and error handling details, but the description is comprehensive given the simple single-parameter input and absence of 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?

The single parameter 'question' is described with examples and clarification of natural language input, adding value beyond the schema's minimal description.

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

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

The description clearly states it answers natural-language questions by routing to the correct data source, and distinguishes it from sibling tools that target specific domains.

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 tells when to use ('What is X?', 'Look up Y', etc.) and implies not to use when you want a specific tool; also lists many sources as context.

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

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

Describes internal fan-out process, classification, and return type. Annotations indicate readOnly and openWorld, and the description aligns perfectly while adding detail not captured by annotations alone.

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

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

Front-loaded with purpose, each sentence informative. Slightly verbose but no redundant phrases. Could be tightened, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description explains return (evidence packet + comparison) and covers inputs, process, and use cases. Comprehensive for a complex research 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% with descriptions, but the description adds value by specifying quick vs thorough depth (not in schema) and clarifying input flexibility. Adds context 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 the tool researches Polymarket bets, specifying input types (slug, URL, question text) and outputs (evidence packet, market-vs-model comparison). It uniquely identifies its role among siblings by focusing on Polymarket betting 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?

Explicit use cases provided: 'should I bet on X?', 'what does the data say?', 'is there edge?'. Lacks explicit when-not-to-use or alternatives, but context is specific enough for an agent to decide.

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 all behavioral traits. It explains the data pulled for each type and mentions return format (paired data + URIs). However, it does not discuss permissions, rate limits, error handling, or data freshness, leaving gaps.

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

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

The description is concise (5 sentences) with no fluff. It front-loads the purpose, then provides usage triggers, then details the two modes. Every sentence adds necessary information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description should clarify the return structure. It says 'paired data + pipeworx:// citation URIs' but does not specify the structure or fields. Also missing error handling for invalid inputs. Adequate but not fully complete for an agent to rely on.

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

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

Schema coverage is 100% for both parameters. The description adds value by explaining the 'type' enum meanings and the 'values' array format with examples (tickers for company, drug names). It goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool's purpose: comparing 2-5 companies or drugs side by side. It specifies the data sources (SEC EDGAR/XBRL for companies, FAERS/FDA/CT for drugs) and distinguishes it from siblings like entity_profile which handles single 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?

The description provides explicit trigger phrases ('compare X and Y', 'X vs Y', etc.) and explains the two entity types. It implies when to use (for side-by-side comparisons) but does not explicitly state when not to use it or mention 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 empty annotations, the description carries full burden but only states the basic purpose. It does not disclose behavioral traits such as whether it is read-only (assumed), rate limits, or error handling.

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

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

The description is a single sentence that front-loads the primary purpose. No wasted words, appropriately concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 4 parameters but no output schema. The description does not explain the return format or behavior when no departures are found, leaving it incomplete.

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 each parameter having a description. The description adds an example for stop_id, which provides additional context, but not significant meaning 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 'Upcoming departures from a stop' which is a specific verb+resource. It distinguishes from sibling tools like search_stops or search_routes by focusing on departures.

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 an example of the stop_id format (Transitland onestop_id), which helps usage, but does not specify when to use this tool over alternatives or any 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 provided, so description carries full burden. It discloses return type (top-N most relevant tools with names+descriptions) but does not mention behavior like performance, no side effects, or that it is read-only. Adequate but not comprehensive.

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

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

Front-loaded with purpose, but includes a long list of domains which could be more concise. Every sentence adds value, but the list makes it slightly verbose.

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 simple purpose (discovery) and good schema coverage, description is fairly complete: explains what it does, when to use, and what it returns. No output schema needed for this type of 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%, so baseline 3. Description does not add meaning beyond schema; it repeats the purpose of query but not limit. No extra context for 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 uses a specific verb 'Find' and resource 'tools' by describing data or task. It clearly distinguishes from sibling tools by stating its role as a discovery/search tool, while siblings are specific actions like ask_pipeworx 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 states when to use: 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' Does not provide explicit when-not-to-use or alternative tools, 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 are provided, so the description carries the burden. It details what the tool returns (SEC filings, financials, patents, news, LEI) and mentions citation URIs. It implies read-only behavior, though it doesn't explicitly state non-destructiveness, but given the context, it is sufficiently transparent.

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-loading the core purpose and then adding usage context. Each sentence is informative, though slightly wordy. Still efficient for the amount of information conveyed.

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 thoroughly explains what is returned (categorically listing items). It covers input constraints and the tool's value proposition (replacing 10+ pack tools). The context is complete for an agent to decide and invoke correctly.

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

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

Schema has 100% coverage with descriptions for both parameters. The description adds value by clarifying that names are not supported and advising use of resolve_entity first. This goes beyond the schema's brief descriptions.

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

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

The description clearly states the verb 'Get' and the resource 'everything about a company'. It distinguishes from siblings like compare_entities and resolve_entity by specifying that this tool provides a comprehensive profile from multiple sources, replacing many 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?

Explicitly lists when to use: user asking 'tell me about X', 'brief me on Tesla', etc. Also provides exclusion: if only a name is available, use resolve_entity first. This gives clear guidance on tool 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?

With no annotations, the description carries the full burden. It states deletion of stored memory, implying destructiveness, but lacks details like permanence or confirmation. Adequate for a simple 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?

Two concise sentences, front-loaded with the action, no unnecessary words. 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?

Complete for a tool with one required parameter, no output schema, and no annotations. Provides purpose, usage context, and sibling references.

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 parameter 'key' is fully described in the schema. Description reiterates 'by key' without adding new meaning beyond 'delete by key'.

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 action (Delete) and resource (memory by key), distinguishing it from siblings like 'remember' and 'recall'.

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 lists use cases: stale context, task complete, or clearing sensitive data. Also mentions pairing with remember and recall for context.

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

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

No annotations provided, and description does not disclose read-only nature, pagination, authentication requirements, or response format. Only states 'available feeds' but no behavioral 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 is concise but lacks structure. It is front-loaded but too minimal; does not earn its place with sufficient detail.

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, no annotations, and only two parameters, the description should provide more context about return format, filtering behavior, and how to interpret results. It is incomplete for effective agent invocation.

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

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

Schema covers 50% of parameters (spec has description, limit lacks description). The tool description adds no additional meaning beyond the schema. For the uncovered parameter (limit), description does not compensate.

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 lists available GTFS feeds across operators, distinguishing it from sibling tools that search entities. However, 'feeds' is slightly vague without specifying whether it returns metadata or identifiers.

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 like search_agencies or search_routes. No context about prerequisites or typical use cases.

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 were provided, so the description carries the full burden. It discloses rate limits (5 per identifier per day), that the tool is free and doesn't count against quota, and that feedback is read daily. However, it doesn't explicitly state that the tool has no side effects aside from storing feedback.

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 multiple pieces of information. While comprehensive, it could be more concise by splitting into sentences or using bullet points.

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 nested parameters, the description covers purpose, usage, parameter details, rate limits, and expected behavior. It is fully adequate for an agent to use the tool correctly.

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

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

Schema coverage is 100%, but the description adds value by elaborating on enum values (e.g., detailing each feedback type) and providing usage tips for the message field. The context object is also explained.

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 is for providing feedback about broken, missing, or needed functionality. It distinguishes itself from sibling tools like ask_pipeworx or discover_tools by specifying its unique purpose.

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

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

The description explicitly lists when to use the tool (bug, feature, data_gap, praise), what not to include (user's prompt), and mentions rate limits and quota info. This provides clear guidance for the agent.

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

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

Annotations already indicate read-only and non-destructive behavior. The description adds value by detailing the internal logic: walking child markets, extracting dates/thresholds, sorting, and reporting violations. No contradictions.

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

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

The description is well-structured, starting with a clear verb phrase and then explaining the concept, mechanism, and output. It is slightly verbose but 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?

With only one simple parameter and no output schema, the description fully covers what the tool does, how to use it, and what results to expect. No gaps remain.

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 only parameter 'event' has 100% schema coverage with description. The description adds context by mentioning slug or URL and providing an example, which is helpful but not extensive.

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: finding arbitrage opportunities via monotonicity violations. It explains the underlying principle with a concrete example and distinguishes it from sibling tools like 'polymarket_edges' which likely do something else.

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 tells the user when to use the tool (to find arbitrage) and how to invoke it (pass an event slug or URL). It doesn't explicitly state when not to use it or mention alternatives, but the context makes it fairly 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?

Annotations indicate readOnlyHint=true, openWorldHint=true, and destructiveHint=false, which the description aligns with by describing a scan and compute process without side effects. The description adds behavioral context by detailing the algorithm (scans top markets, groups by asset, fetches price history once, computes model probability, ranks by |edge|) and data sources (FRED, coinpaprika). It lacks some details like error handling or rate limits, but overall provides meaningful transparency beyond annotations.

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

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

The description is a single paragraph of five sentences, each serving a purpose: stating the main action, explaining the model version, describing the algorithm steps, specifying the output, and stating the use case. No redundant or superfluous 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 adequately explains the return value ('top N ranked by edge magnitude with suggested trade direction'). It also covers data sources, model type, parameter roles, and annotations. The description is comprehensive for a read-only discovery 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 has 100% description coverage, so the schema already documents the parameters (limit, window, min_edge_pp) with clear descriptions. The description adds minimal additional context beyond what is in the schema, such as clarifying that limit returns 'top N edges'. Since schema coverage is high, a baseline of 3 is appropriate.

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

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

The description clearly states the tool scans high-volume Polymarket markets and returns those where Pipeworx data disagrees most with market price. It specifies the data sources (lognormal model from FRED + live coinpaprika price) and the algorithm steps. It distinguishes itself from siblings by explicitly stating its use case: 'Built for the "what should I bet on today" question.'

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 the tool is designed for discovering betting opportunities without manual browsing. It implies when to use: when users/agents need to find markets with high edge. However, it does not provide explicit guidance on when not to use or mention alternative sibling tools like polymarket_arbitrage.

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 full behavioral disclosure. It explains the retrieval behavior, effect of omitting key (list all), scoping, and pairing with other tools. It lacks details on failure cases or rate limits, but the core behavior is transparent.

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 main purpose. Every sentence adds value: retrieval behavior, usage context, and pairing advice. 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?

Despite no output schema, the description covers the tool's purpose, usage guidelines, parameter behavior, scoping, and relationship with siblings. It lacks details on return format or error handling, but is fairly complete for a simple retrieval 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%, so baseline is 3. The description adds minimal new meaning beyond the schema's parameter description; it reiterates the option to omit the key to list all keys, which is 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's two behaviors: retrieving a specific saved value or listing all keys. It uses specific verbs ('retrieve', 'list') and resource ('saved keys'), and distinguishes from siblings 'remember' and 'forget'.

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

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

The description explicitly tells when to use (to look up stored context) and when not to (by pairing with siblings for save/delete). It also notes scoping and provides concrete examples like 'target ticker, address, research notes'.

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 discloses the fan-out to three sources, the input date format, and the output structure (changes + count + URIs). It doesn't mention rate limits or auth but is transparent about core 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 efficiently structured with a question lead, usage examples, then technical details. Every sentence contributes value 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 no output schema, the description adequately explains return structure. It covers purpose, parameters, data sources, and output format. Could mention error handling or empty results, but overall 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 coverage is 100%. The description adds meaning by explaining the since parameter's date formats and typical values, clarifying value can be ticker or CIK, and noting type is currently limited to 'company'.

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 answers 'What's new with a company' and provides specific query patterns. It distinguishes from sibling tools like entity_profile by focusing on temporal changes across multiple data sources.

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

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

The description gives explicit usage examples ('use when a user asks ...') and covers the fan-out behavior. It doesn't explicitly exclude alternatives, but the examples and context imply the appropriate use case.

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 key behavioral traits: key-value pair scoped by identifier, persistent memory for authenticated users, 24-hour retention for anonymous sessions. No annotations provided, so description carries burden, but it's well-covered.

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

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

Concise at ~80 words, front-loaded with purpose, and every sentence adds value with 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?

Completeness is high given simple tool and no output schema: explains storage duration, scoping, and pairing with siblings. Could mention success/error responses but not required for typical 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 key and value. Description adds context by providing example key patterns and explaining value can hold any text, enriching 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?

Description clearly states 'Save data the agent will need to reuse later' with specific verb and resource, and distinguishes from siblings recall and forget.

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

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

Explicitly states when to use (discover worth carrying forward) and pairs with recall to retrieve and forget to delete, providing clear guidance on alternatives.

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

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

No annotations provided, so description carries full burden. It discloses that the tool returns IDs and 'pipeworx:// citation URIs', indicating a read operation. It does not mention auth or rate limits, but overall 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?

The description is three sentences plus an example, well-structured and front-loaded. While every sentence adds value, minor redundancy exists (e.g., 'Use this BEFORE...' slightly overlaps with earlier advice). Still highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (two entity types, multiple ID systems), the description is complete. It explains input format, output details (IDs + citation URIs), and notes it replaces 2-3 calls, without relying on an 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% with both parameters described. The description adds context beyond the schema: for 'type' it restates enum values, and for 'value' it explains accepted formats with examples (AAPL, 0000320193, ozempic), enhancing understanding.

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

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

The description clearly states the tool's purpose: 'Look up the canonical/official identifier for a company or drug.' It names specific ID systems (CIK, ticker, RxCUI, LEI) and gives examples, distinguishing 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?

The description provides explicit usage guidance: 'Use when a user mentions a name and you need the CIK... the ID systems that other tools require as input.' It also advises to use this tool BEFORE calling other tools that need identifiers.

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 read-only search operation, but with no annotations, it lacks details on pagination, rate limits, or interaction between parameters. It is adequate but minimal.

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, concise sentence that front-loads the core purpose with 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 six parameters and no output schema, the description is brief and does not clarify parameter interactions (e.g., how name and geo filters combine). Adequate 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 coverage is 100%, and the description merely echoes 'by name or geo' already implied by the schema. No additional semantic value beyond the 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 the tool searches transit agencies/operators by name or geo, using a specific verb and resource, and distinguishes from sibling tools like search_routes and search_stops.

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 by mentioning 'Operators are the entities running services', but does not explicitly state when to use this tool versus alternatives or provide 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?

Description only mentions it is a 'search' operation. No annotations provided. No disclosure of side effects, permissions, rate limits, pagination, or required filters. Behavioral transparency is minimal.

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 one concise sentence with an inline list. No wasted words, but could be slightly better structured (e.g., grouping optional vs. required filters).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters and no output schema, description should explain parameter interactions, default behavior, and result format. Only route_type is elaborated. Lacks details for complete understanding.

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?

Adds value by listing route_type code mappings, which the schema only names. However, schema coverage is only 25%, and parameters like lat, lon, limit, etc. are not explained beyond their names. Does not fully compensate for low coverage.

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 searches routes by multiple criteria (name, type, agency, location). It is specific to 'routes', but does not explicitly differentiate from sibling tools like search_stops.

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 like search_stops or search_agencies. Implies general route search but lacks exclusions or prerequisites.

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

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

Annotations are empty, so the description bears full responsibility. It does not disclose important behavioral aspects: default behavior when no parameters are provided, pagination, result ordering, or any side effects. The brief wording lacks transparency for a tool with 7 optional parameters.

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 very short (two sentences), which is concise, but it sacrifices necessary information. While no filler is present, the brevity leaves gaps that reduce overall helpfulness.

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 7-parameter tool with no output schema and no annotations, the description is incomplete. It only covers one specific search mode (lat/lon/radius) and ignores other parameters like name, stop_id, and limit. The tool's complexity demands a richer description.

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 43% (stop_id, radius_m, served_by_route_type have descriptions). The description adds context for lat, lon, and radius_m as a combined use case, but does not explain name, limit, or how multiple parameters interact. This provides some added value over the schema but is incomplete.

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 ('Search stops/stations') and provides a specific use case ('stops near point') using lat+lon+radius_m. It distinguishes from sibling tools like search_agencies and search_routes, which focus on different 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?

The description gives a single concrete scenario (lat+lon+radius_m for nearby stops) but does not explain when to use name, stop_id, or other parameters. No guidance on when not to use this tool versus alternatives like search_routes or departures_at_stop.

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 covers the return value (verdict, actual value, citation) and notes it is a non-destructive, efficient replacement for multiple calls. It does not mention rate limits or error cases, but sufficient given the tool's simplicity.

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 redundancy. Action verb in first sentence, followed by usage examples and domain info. 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?

For a single-parameter tool with no output schema, the description fully explains purpose, trigger, domain, return format, and efficiency benefit. No major 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 a clear description and examples. The description adds context about supported claim types (company-financial) but does not significantly enhance understanding of the single parameter 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?

Description states a specific verb (fact-check/validate), resource (factual claims against authoritative sources), and scope (company-financial for US public companies). It clearly distinguishes from sibling tools which are for entity profiles, comparisons, or other tasks.

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 'Use when an agent needs to check whether something a user said is true' and provides example queries. It notes the domain restriction, but does not explicitly state when not to use or mention alternatives among siblings.

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