Microsoft Todo

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

Annotations declare readOnly/openWorld/idempotent. Description adds return format, cost details (free vs BYO key), and output structure. 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?

Concise, front-loaded with purpose, then pricing/model details, then output structure. 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?

Covers purpose, input parameters, default behavior, optional key, return format. Lacks comparison to similar sibling tools or error conditions, but given annotations and schema completeness, it's 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?

Schema covers all parameters with descriptions. Description adds minimal extra semantics (e.g., default model, API key pass-through). Baseline 3 due to high schema 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?

The description clearly states it probes LLMs for entity knowledge and scores visibility. It distinguishes from similar tools implicitly through its focus on multi-model scoring, but lacks explicit sibling differentiation.

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

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

Provides usage context (AI-marketing audits, brand checks) and explains optional Anthropic probing with BYO key. Lacks when-not-to-use or comparison to alternatives like scan_competitor_ai_presence.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds that it routes to 3,336 tools across 747 sources, fills arguments, and returns citations with pipeworx:// URIs. No contradiction. Additional context about the scale and routing behavior is valuable.

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 dense paragraph but well-structured, starting with the most important directive. Each sentence adds value, listing data types, scale, and examples. Slightly lengthy but 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 no output schema, the description mentions structured answers and citation URIs, hinting at return format. It covers the main question parameter and examples. Missing details on edge cases or error handling, but sufficient for a read-only, open-world tool with good annotations.

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

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

Schema description coverage is 100% with all parameters having clear descriptions. The description provides examples of questions but does not add significant new semantics beyond what the schema already offers. 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 answers factual questions from authoritative structured data, with specific examples. It distinguishes itself from web search by explicitly preferring over web search for certain queries, making the purpose unambiguous.

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

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

The description explicitly says 'PREFER OVER WEB SEARCH' and lists many scenarios (SEC filings, FDA data, etc.) and example user intents. It does not explicitly state when not to use, but provides strong guidance on when to use, which is clear enough for an 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 readOnly, idempotent, openWorld, non-destructive. The description adds extensive behavioral details: fan-out examples, response shapes, resolver contract (match confidence, alternatives), parent event extraction, news fallback mechanisms, safety handling (low-confidence, closed markets, wide spreads). No contradictions with annotations.

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

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

The description is verbose and packed with detailed examples and edge cases. While well-structured with sections and examples, it is quite long and could be more concise. Some details (like specific fan-out examples for each classifier) could be condensed without losing essential guidance.

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 fully documents the return value shape: result.market fields, result.analysis fields, result.evidence keyed by source, resolver contract (match confidence, score, alternatives, suggestions), parent event extractor details, news fields with fallback info. It also explains safety mechanisms and status codes, making it complete for agent 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%, so baseline 3. Description adds value beyond schema by explaining the depth parameter enum values (quick vs thorough), the market parameter input types (slug, URL, question text) with examples, and the include_raw parameter effect on response size. The examples and context enhance 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?

Description clearly states the tool researches a Polymarket bet by pulling Pipeworx data, with specific verb+resource. It differentiates from siblings by its comprehensive approach: resolving, classifying, fanning out to multiple data sources, and returning an evidence packet. No other sibling tool offers this integrated research capability.

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: 'should I bet on X', 'what does the data say about Y', 'is there edge in Z'. It implies use when you need comprehensive data about a specific bet. Does not explicitly state when not to use it or list alternatives, but the clear use cases provide adequate guidance.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds key behavioral details: data sources (SEC EDGAR, FAERS, FDA), exact financial metrics and adverse event counts, sorting by primary metric, and handling of off-calendar fiscal years. Rich context 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?

Well-structured: core function first, then usage, then details per type, then summary benefit. Slightly verbose with minor parenthetical like 'post-Run-6 fix' which may be unnecessary, but overall 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?

Even without output schema, description fully explains return format: paired data with pipeworx:// URIs and sorted results. Covers both entity types completely. No missing information for correct 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 descriptions are complete (100% coverage). Description amplifies by explaining 'values' array format (tickers/CIKs for company, drug names) and constraints, and how 'type' determines data source and metrics. Adds significant value 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?

Clearly states it compares 2-5 companies or drugs side by side, pulling financial or adverse-event data. Use cases like 'compare X and Y', 'which is bigger' are given. Differentiates from sibling tools like resolve_entity which handle 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?

Explicitly says when to use: for comparison and ranking queries, and that it replaces 8-15 sequential lookups. No when-not-to-use or alternatives, but context is clear enough for an AI 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?

Discloses that it returns top-N most relevant tools with names, descriptions, and full input schemas (with curated examples), and notes each result is 'ready to call directly.' This adds valuable behavioral info beyond the annotations (readOnlyHint, idempotentHint, destructiveHint). No contradiction.

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

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

Concise two-sentence description plus a list of domains. Every sentence is informative. Front-loaded with the core 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 tool's complexity (discovery across many domains), the description fully covers purpose, usage, and output. The schema covers all parameters. No output schema needed as return values are described.

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 provides examples and clarifies that 'query' accepts natural language descriptions. This adds meaning beyond the aliases listed 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?

Description clearly states the tool's purpose: 'Find tools by describing the data or task.' It lists many domains (SEC filings, FDA drugs, etc.) and emphasizes discovery. This distinguishes it from siblings, which are more specific 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 instructs 'Call this FIRST when you have many tools available and want to see the option set.' This provides clear context for when to use it, though it doesn't explicitly say when not to use it.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive behavior. The description adds significant context: specific return fields (cik, filings with URIs, fundamentals with data caveats, patents sunset, news fallback, LEI). It discloses failure modes (patents soft-fail). This goes beyond annotations but could be slightly more explicit about potential inconsistencies from open-world hint.

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 dense paragraph but every sentence adds value. It could be more structured (e.g., bullet points or sections), but it is front-loaded with purpose and usage. Not overly verbose; earns its length.

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 return values, including fields, data caveats, and fallback mechanisms. It also covers input constraints and alternative tools. Comprehensive for a complex tool with many dependencies.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining 'value' expects ticker or zero-padded CIK, explicitly states names not supported, and advises using resolve_entity. It also clarifies that 'type' only supports 'company' currently. This exceeds schema information.

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

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

The description clearly states the tool's purpose: 'Get everything about a US public company in one call.' It specifies when to use it (user asks for company info, avoids calling 10+ pack tools) and distinguishes from siblings like resolve_entity by noting name inputs are not supported.

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 usage guidance: 'Use when a user asks "tell me about X", "research Acme", "brief me on Tesla".' Also provides when-not-to-use: 'names not supported (use resolve_entity first).' This is comprehensive and helps the agent select the right tool.

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 aligns with annotations (destructiveHint=true) and adds useful behavioral context (clearing sensitive data). No contradictions.

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

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

Three concise sentences covering action, usage, and related tools. No 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?

For a simple tool with one parameter and no output schema, the description fully covers purpose, usage, and relationships with sibling tools.

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

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

Schema description coverage is 100% and the parameter 'key' is well-described. The description adds context about 'previously stored memory', which slightly enhances 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 action ('Delete a previously stored memory by key') and distinguishes from siblings like 'remember' and 'recall' by mentioning them together.

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 ('context is stale, task is done, clear sensitive data') and provides pairing advice with 'remember' and 'recall'.

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

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

Annotations declare readOnlyHint, idempotentHint, and no destructiveness. The description adds that it fetches the page and extracts content, which aligns and provides process context.

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

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

The description is a single focused paragraph with no redundant sentences. Each sentence adds meaningful 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 rich annotations and full schema coverage, the description is complete: it explains the output format and use cases, leaving no ambiguity for an 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%, so the description adds minimal value beyond what the schema provides. The description does not expand on parameters beyond 'Full URL'.

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 generates an llms.txt file for any URL, specifies the output format, and lists use cases. No sibling tool has overlapping functionality.

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

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

The description explicitly lists three use cases (client indexing, own project, competitor audit) but does not mention when not to use it 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?

The description adds significant behavioral context beyond annotations: it discloses rate limits (5 per day), that it's free and doesn't count against tool-call quota, and that the team reads digests. Annotations only show readOnlyHint=false and destructiveHint=false.

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 somewhat long but well-structured with clear recommendations. It front-loads the purpose and uses bullet-like enumeration for feedback types. Could be slightly tighter but still effective.

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

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

The description covers usage, constraints, and intent comprehensively. With no output schema, it explains the feedback lifecycle. The nested context object is adequately described. Slight room for improvement in explaining what happens after submission.

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 parameters are already documented. However, the description adds valuable usage context (e.g., 'don't paste the end-user's prompt', 'describe in terms of Pipeworx tools/packs') that 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 explicitly states the tool collects feedback about bugs, missing features, data gaps, or praise. It uses specific verbs and clearly distinguishes from sibling tools by being a feedback channel.

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

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

The description provides clear when-to-use guidance for each feedback type (bug, feature, data_gap, praise) and specifies what not to do (e.g., don't paste end-user prompts). It also mentions rate limits and that it's free.

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

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

Annotations already declare readOnly, openWorld, idempotent. The description adds value by disclosing the data source (CF analytics engine), no PII, and caching behavior (5min-1h). 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?

Description is front-loaded with main purpose and uses bullet points for use cases. Slightly verbose but well-structured and informative.

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 exists, but the description covers return content (top tools, packs, volume), data source, privacy, and caching. Fully sufficient for the tool's complexity.

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

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

Schema coverage is 100% for the single parameter with an enum. The description adds context about shorter vs longer windows, enhancing 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 it returns top tools, top packs, and total call volume over a recent window. It distinguishes from sibling tools like 'discover_tools' and 'ask_pipeworx' by focusing on trending usage data.

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?

Three explicit use cases are provided: discovering hot data sources, confirming canonical tools, and seeing alignment. While it lacks explicit when-not-to-use guidance, the listed scenarios are clear and actionable.

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

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

Annotations indicate read-only, open-world, idempotent, non-destructive behavior. Description adds substantial behavioral context: Jaccard similarity threshold (≥0.30), placeholders filter (>20% placeholder fraction returns null), response structure with opportunities and partition_check, and cross-event mode details. 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?

Description is organized with clear sections (modes, semantic anchor, partition filter, response). While somewhat long, every sentence adds necessary detail for a complex tool. Could be slightly more concise, but structure is effective.

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, description fully covers input modes, constraints, and response structure (opportunities array with fields, partition_check object). For a tool with 2 parameters and complex logic, this is complete and self-contained.

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

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

Schema coverage is 100% and both parameters have descriptions. Description goes further by explaining the mode context for each parameter (e.g., 'event' for single-event mode, 'topic' for cross-event mode), adding value beyond the schema.

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

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

Description clearly states it finds arbitrage opportunities via monotonicity violations and partition-sum checks. It distinguishes two specific modes (event and topic) with detailed explanations, making the purpose very clear and distinct 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?

Provides explicit guidance on when to use each mode (event for single event, topic for cross-event). Describes semantic anchor and partition filter constraints. No explicit when-not-to-use, but context is sufficient for competent 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?

Annotations (readOnlyHint=true, destructiveHint=false) are consistent with the description's read-only scan. The description adds behavioral context: caching (KV level, 1h), diagnostic output for empty segments, and warning about Fed bets being unreliable. No contradiction.

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

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

The description is very detailed but verbose, with dense technical explanations (e.g., math formulas, segments). It is well-structured with sections but could be more concise for quick comprehension.

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 (9 parameters, no output schema), the description covers output structure, segments, diagnostics, caching, and data limitations. It provides enough context for an agent to understand return values and behavior.

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

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

Schema coverage is 100% with descriptions. The description adds significant value: explains slippage context (Polymarket fees), min_partition_leg_kelly logic (partition arbs don't compose to single-leg Kelly), and tradeable-edge knobs. This goes 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 explicitly states the purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It distinguishes from siblings like polymarket_arbitrage by detailing three specific segments (model_driven, structural_arbitrage, concentrated_longshot) and internal logic.

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 clearly states when to use the tool: 'Built for "what should I bet on today" — agents discover opportunities without paging hundreds of markets.' It also explains filter knobs. However, it does not explicitly exclude alternatives or provide when-not-to-use scenarios.

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

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

Annotations already mark it as read-only and idempotent. The description adds extensive behavioral detail: it explains how spreads are computed, the meaning of compatibility_warning (two cases), temporal_alignment, and skipped counters. Very 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 lengthy but well-structured, starting with purpose, then modes, then response details. Every sentence adds value, though some redundancy could be trimmed for brevity.

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 the response format, safety fields, and edge cases. It covers everything an agent needs to interpret results 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 all three parameters. The description adds significant context beyond schema, e.g., explaining the topic list values, how explicit tickers override, and response structure including safety fields.

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 computes cross-venue spreads between Kalshi and Polymarket for the same question. It distinguishes itself from siblings by focusing on intra-question comparison across venues, with two explicit modes and detailed response structure.

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 clear guidance on when to use topic shortcuts vs explicit tickers, and warns that most pre-mapped topics are not tradeable. However, it does not explicitly contrast with sibling tools like polymarket_arbitrage or polymarket_edges.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds scope (anonymous IP, BYO key hash, account ID) and pairing with save/delete tools, enhancing 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?

Three sentences, front-loaded with purpose. Second sentence explains usage, third adds scope and relationships. No redundant or unnecessary content.

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 tool with one optional parameter, description is complete. Covers behavior with/without key, scope, and pairing with remember/forget. No output schema, but return value is 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?

Schema coverage is 100%, but description adds meaning: explains that omitting key lists all keys, and that key is used to retrieve a specific value. This goes beyond the schema's type/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?

Clearly states it retrieves saved values via 'remember' or lists all keys. Distinguishes from sibling tools 'remember' and 'forget' by specifying its retrieval role and the effect of omitting key.

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 to use for looking up context stored earlier without re-deriving. Describes listing behavior when key omitted. Does not explicitly state when not to use, but context is clear for a simple retrieval tool.

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

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

Annotations already declare readOnlyHint=true, openWorldHint, idempotentHint, and destructiveHint=false. The description goes beyond by disclosing parallel fan-out to multiple sources, fallback mechanisms, and a pending API sunset, providing rich behavioral context not captured in 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 cohesive paragraph but packs in purpose, usage, parallelism, parameters, fallbacks, and output format without extra fluff. Slightly dense but every sentence contributes unique information. Could be broken into smaller sentences for readability, 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?

Despite no output schema, the description explains the return structure (changes array grouped by source, total_changes count, citation URIs). It covers the tool's complexity: multiple data sources, fallback behavior, parameter constraints, and alternative tools, making it fully informative for an 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?

With 100% schema description coverage, the description still adds value by clarifying accepted formats for 'since' (ISO date vs relative shorthand with examples), acceptable values for 'value' (ticker or CIK), and constraints for 'type' (only company). This helps the agent prepare correct inputs.

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

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

The description uses a clear verb phrase 'What's new with a company in the last N days/months?' and provides concrete use cases like 'updates on Y' and 'news on Apple this month'. It explicitly distinguishes from the sibling tool entity_profile, stating when to use the alternative instead.

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 guidance, listing example queries and specifying when not to use this tool ('Use entity_profile instead when you want the static profile'). It also details fallback logic (GDELT→GNews) and soft-failure behavior (USPTO PatentsView API sunset), aiding correct 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?

Annotations indicate idempotentHint=true and destructiveHint=false; description adds persistence details (authenticated vs anonymous sessions, 24-hour retention). No contradiction.

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

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

Description is concise and well-structured: purpose first, then usage guidance, then technical details. Every sentence adds 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?

For a simple tool with 2 parameters and no output schema, the description covers purpose, behavior, persistence, and pairing with sibling tools completely.

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

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

Schema has 100% coverage with descriptions for both key and value. Description reinforces key-value pair concept and adds scoping context, slightly exceeding baseline.

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 explicitly states the tool saves data for reuse later, with concrete examples like tickers, addresses, preferences. It 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?

The description clearly says when to use ('discover something worth carrying forward') and pairs with recall and forget for retrieval and deletion.

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

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

The description discloses that each call cascades through multiple lookup endpoints internally and replaces 2-3 manual lookups. It details the exact return data per type (e.g., ticker, CIK, citation URI for company). This adds significant value beyond the annotations (which already indicate read-only, idempotent, non-destructive behavior) and does not contradict any annotations.

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

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

The description is concise—two sentences plus a list of supported types—and front-loaded with the primary purpose and usage directive. Every sentence adds value without repetition or unnecessary 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 the tool's moderate complexity (2 parameters, no output schema), the description fully explains what each type returns and the autodisambiguation feature. It covers all necessary context for an agent to use the tool correctly, including internal behavior (cascading lookups) and replacement of manual steps.

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 100% coverage, so baseline is 3. The description adds meaning by explaining that the 'value' parameter accepts ticker, CIK, or company name (for company) and brand or generic name (for drug), and mentions auto-disambiguation. This contextual enrichment justifies a score above baseline.

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 'Resolve a user-spoken name to the canonical/official identifiers' with a specific verb and resource. It also advises 'Use FIRST when you have a name but need an ID', which distinguishes it from other tools that might use IDs or provide different services.

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

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

The description explicitly says 'Use FIRST when you have a name but need an ID', providing a clear usage scenario. It implies this tool should be used before other tools that require IDs. However, it does not explicitly list when not to use it or name alternative tools, leaving some room for improvement.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint (no destructive actions). The description adds useful context: it internally calls ai_visibility_check, ranks results, and surfaces most/least recognized entities. It details output fields (score, confidence, signal density). While it doesn't cover rate limits or API key usage limits, the annotations reduce the burden.

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: the first states the core function and process, the second provides a concrete use case and output summary. Every sentence adds value with no wasted words. Well front-loaded and structured.

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

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

For a tool with 4 parameters (1 required) and no output schema, the description adequately covers purpose, usage scenario, parameter roles (including default behavior), and return fields. It also explains the internal probe mechanism. Slight gap is the lack of error handling or limits, but overall complete given the provided context.

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 meaning by clarifying that the first entity in the array is treated as the 'subject' for narrative and that omitting 'models' defaults to workers-ai. This enhances the understanding beyond schema 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 compares AI visibility across multiple entities side-by-side, using 'ai_visibility_check' for probes and ranking by score. It provides a concrete use case ('does Claude know about us as well as our competitors?'), distinguishing it from siblings like 'ai_visibility_check' (single entity) and 'compare_entities' (general comparison).

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 indicates it's for competitive AI-marketing audits and implies side-by-side comparison (2-8 entities). It does not explicitly state when not to use or contrast with alternatives, but the example question and the mention of 'your brand + N competitors' make the context clear. Lacks explicit exclusion 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?

Beyond annotations (readOnlyHint, idempotentHint), the description discloses that it fans out to multiple sources, returns a specific summary block, handles partial failures gracefully, and notes that bundlephobia's first measurement can take 5-30 seconds. This provides rich behavioral context.

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

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

The description is lengthy but well-structured: first sentence states purpose, then usage scenario, then output details, then limitations. It is front-loaded and every sentence provides value, though it could be trimmed slightly.

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 (multiple sources, rich output) and no output schema, the description fully explains what is returned (summary block, advisory details, links, alternative versions). It covers ecosystem scope and failure behavior, making it complete for an agent to invoke correctly.

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

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

Schema coverage is 100%, so the schema already documents both parameters thoroughly. The description slightly reinforces that scoped packages are accepted and version defaults to latest, but adds no new semantic 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 it performs a composite check for npm packages, covering license, advisories, bundle size, and more. It uses a specific verb 'scan' and resource 'dependency', and its uniqueness is evident as no sibling tool covers npm package analysis.

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: when an agent asks about safety, popularity, size, or cost of adding an npm package. It also notes limitations (NPM only v1, partial failures, timing). However, it does not explicitly mention when not to use it or provide alternative tools for other ecosystems.

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 data source (SEC EDGAR + XBRL), return types (verdict, structured form, actual value with citation, percent delta), and efficiency benefit (replaces 4–6 calls). Annotations (readOnlyHint, idempotentHint) are consistent and enhanced.

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?

Five concise sentences, front-loaded with purpose, then usage guidance, domain limits, and output summary. No redundant or unnecessary text.

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 single parameter and no output schema, description fully explains input, processing, and output. No gaps for effective tool 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 the single parameter with a clear description. The tool description adds extra examples, reinforcing expected format and usage, going beyond schema baseline.

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 the tool fact-checks natural-language claims against authoritative sources, specifies domain (company-financial claims for US public companies), and distinguishes via replacement of multiple sequential calls.

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

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

Provides explicit usage context with examples ('Use when an agent needs to check...') and example phrases, though does not explicitly state when not to use or list alternatives.

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