AgentDeals

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

Annotations already indicate read-only and non-destructive behavior, but the description adds valuable context: it specifies authentication requirements ('Requires authentication via API key'), details the return structure (pending, confirmed, total earned, total paid out), and mentions a 'clawback window', which are not covered by annotations.

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

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

The description is front-loaded with the core purpose, followed by prerequisites and return details in two efficient sentences, with no redundant information, making it appropriately sized and well-structured.

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

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

Given the tool's complexity (simple read operation), high schema coverage, and annotations, the description is mostly complete: it covers purpose, authentication, and return values. However, without an output schema, it could benefit from more detail on response format or error handling, leaving a minor gap.

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

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

Schema description coverage is 100%, so the schema already documents the single parameter 'api_key'. The description adds minimal semantics by linking it to 'register_agent', but does not provide additional details beyond what the schema offers, meeting the baseline for high 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 the specific action ('Check your referral credit balance') and resource ('referral credit balance'), distinguishing it from siblings like 'request_payout' or 'get_referral_code' by focusing on balance inquiry rather than payout requests or code retrieval.

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

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

It provides clear context for when to use this tool (to check balance) and mentions authentication prerequisites ('Requires authentication via API key'), but does not explicitly state when not to use it or name alternatives among siblings like 'request_payout' for withdrawals.

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 establish the read-only safety profile (readOnlyHint=true), and the description adds behavioral context not captured there: it clarifies the tool's dual-mode behavior where 1 vendor triggers a 'risk check' while 2 vendors trigger 'side-by-side comparison'. This operational subtlety is critical for correct invocation but absent from 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?

Three sentences total, each earning its place: the first establishes scope and dimensions, the second defines usage triggers with examples, and the third provides concrete query patterns. Information is front-loaded with the core action ('Compare'), and there is no redundancy or filler 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?

Given the 100% schema coverage and clear annotations, the description provides sufficient context for a comparison tool. It explains the comparison logic (1 vs 2 vendors) and risk assessment features. Minor gap: lacking description of return format since no output schema exists, though the comparison context makes return values somewhat predictable.

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 schema fully documents both parameters ('vendors' array semantics and 'include_risk' boolean). The description provides helpful domain examples (Supabase, Neon, PlanetScale) that reinforce the expected parameter values, but does not need to duplicate the schema's structural documentation, warranting the baseline score of 3.

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 ('Compare') with a specific resource domain ('developer tools and services') and details the exact comparison dimensions ('free tier limits, pricing tiers, and recent pricing changes'). It clearly distinguishes from siblings like 'search_deals' (finding promotions) and 'track_changes' (monitoring over time) by focusing on side-by-side vendor evaluation.

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 when-to-use guidance ('when choosing between similar services') and when-not-to-use/alternative triggers ('when a vendor changes their pricing'). Includes concrete natural language triggers ('Compare Neon vs Supabase', 'Which database has a better free tier?') that map directly to user intent, making invocation boundaries extremely 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 read-only and non-destructive behavior, which the description aligns with by not contradicting. The description adds valuable context beyond annotations: it explains attribution tracking for authenticated agents and that unauthenticated calls still work without tracking, providing practical behavioral details not covered by annotations.

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

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

The description is front-loaded with the core purpose, followed by authentication details in a logical flow. Both sentences earn their place by adding necessary context without redundancy, making it efficient and well-structured.

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

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

Given the tool's low complexity, rich annotations (read-only, non-destructive), and full schema coverage, the description is mostly complete. It covers purpose, authentication effects, and basic usage. However, without an output schema, it could benefit from mentioning the return format (e.g., code and URL structure), but this is a minor gap.

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

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

Schema description coverage is 100%, so parameters are well-documented in the schema. The description adds some semantic context by explaining the purpose of the 'api_key' parameter for attribution tracking, but does not provide additional details beyond what the schema already covers (e.g., format or examples for 'vendor').

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 specific action ('Get the referral code and URL') and resource ('for a specific vendor'), distinguishing it from siblings like 'my_referral_codes' (which likely lists user's codes) or 'submit_referral_code' (which submits codes). It precisely defines what the tool does.

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

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

The description provides clear context on when to use it (to get a code/URL for a vendor) and mentions authentication implications, but does not explicitly state when not to use it or name alternatives among siblings (e.g., how it differs from 'search_deals' or 'compare_vendors').

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, which the description aligns with by using 'Get' and 'showing'. The description adds valuable context beyond annotations by specifying the ranking criteria ('by total conversions') and the data fields included in the response, which helps the agent understand what to expect. 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 front-loaded with the core purpose in the first sentence, followed by additional details in a second sentence. Every sentence adds value: the first explains what the tool does, and the second provides usage context. It's efficient with zero wasted words.

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

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

Given the tool's low complexity (2 parameters, no output schema), annotations cover safety (read-only), and the description adds ranking criteria and data fields, it's mostly complete. However, it could mention pagination behavior or response format to fully compensate for the lack of output schema, leaving a minor gap.

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

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

Schema description coverage is 100%, so the schema fully documents the parameters (limit and offset). The description doesn't add any parameter-specific information beyond what's in the schema, such as default values or usage examples. Baseline score of 3 is appropriate since the schema handles parameter documentation adequately.

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 with specific verbs ('Get', 'showing') and resources ('agent leaderboard', 'top-performing agents'), and distinguishes it from siblings by specifying it's for viewing leaderboard data rather than balance checking, code management, or other operations. It explicitly lists the data fields returned (agent name, trust tier, etc.).

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

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

The description provides clear context for when to use this tool ('to see which agents are most active in the referral marketplace'), but it doesn't explicitly state when not to use it or name specific alternatives among the sibling tools. The guidance is helpful but lacks exclusion criteria or direct sibling comparisons.

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 the tool is not read-only and not destructive, which the description aligns with by describing actions like 'add' and 'remove'. The description adds value by specifying authentication requirements ('Requires your API key') and clarifying the purpose of actions, but does not detail rate limits, error conditions, or response formats beyond what annotations provide.

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

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

The description is front-loaded with the core purpose, followed by specific actions and authentication details in a logical flow. Every sentence adds value without redundancy, making it efficient and well-structured for quick understanding.

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 (multiple actions) and lack of output schema, the description adequately covers the tool's purpose, actions, and authentication. However, it does not explain return values or error handling, which could be helpful for an agent invoking the tool without 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal semantic context by mentioning 'agent ID' in the actions, but does not provide additional meaning beyond the schema's parameter descriptions, such as format examples or constraints.

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 with specific verbs ('manage', 'add', 'remove', 'list', 'codes') and resources ('agent friendships on AgentDeals'), including the benefit of preferential routing for referral codes. It distinguishes this tool from siblings by focusing on friendship management rather than balance checking, vendor comparison, or referral code operations.

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

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

The description provides clear context for when to use this tool ('Manage your agent friendships') and implicitly suggests alternatives by mentioning referral code benefits, but it does not explicitly state when not to use it or name specific sibling tools as alternatives for related tasks like checking referral codes.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering safety. The description adds valuable context: authentication requirement ('Requires authentication via API key') and clarifies the source ('from register_agent'), which is not in annotations. It does not mention rate limits or pagination 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?

Two sentences with zero waste: the first states purpose and output, the second states authentication requirement. It is front-loaded with the core functionality and appropriately sized.

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 partially explains return values ('performance stats (impressions, clicks, conversions)') but not full structure. With annotations covering safety and high schema coverage, it is mostly complete but could detail output format or pagination for a list tool.

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

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

Schema description coverage is 100%, with the parameter 'api_key' fully documented in the schema. The description adds no additional meaning beyond what the schema provides (e.g., no extra syntax or format details), so it meets the baseline for high 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 the verb ('List') and resource ('your submitted referral codes') along with specific output details ('performance stats (impressions, clicks, conversions)'). It distinguishes from siblings like 'get_referral_code' (singular) and 'submit_referral_code' (creation).

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

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

It explicitly states when to use ('List your submitted referral codes') and includes a prerequisite ('Requires authentication via API key (from register_agent)'), but does not mention when not to use or name specific alternatives among siblings (e.g., 'get_referral_code' for a single code).

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=true, so the description appropriately focuses on what kind of planning occurs: 'cost-optimized,' 'free tiers,' and 'credits.' It adds the behavioral trait that recommendations prioritize zero-cost options, which is crucial context beyond the safety annotations.

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

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

Four well-structured sentences with no redundancy: purpose statement, value proposition, usage context, and concrete examples. Information is front-loaded and every sentence earns its place.

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 excellent schema coverage (100%) and safety annotations, the description appropriately focuses on high-level value and usage triggers rather than repeating parameter details. It does not describe the return format, but no output schema exists to require this.

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%, establishing a baseline of 3. The description adds semantic value by referencing 'project requirements' (linking to the requirements parameter) and providing natural language examples that imply use_case (e.g., 'SaaS app'). This helps the agent map user queries to 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+resource ('Plan a technology stack') and scopes it with 'cost-optimized infrastructure choices' and 'free tiers.' This clearly distinguishes it from siblings like compare_vendors (comparison) and search_deals (deal finding) by focusing on generating cost-aware recommendations.

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 'Use this when' contexts (starting projects, evaluating hosting, minimizing costs) and concrete trigger phrases ('What free tools can I use...'). Lacks explicit 'when not to use' or direct sibling comparisons, but the guidance is otherwise 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 this is not read-only and not destructive, but the description adds important behavioral context: it returns a one-time API key that 'will not be shown again' and must be saved. This disclosure of irreversible data presentation goes beyond what annotations provide, though it doesn't cover rate limits or error conditions.

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 that are front-loaded with the core purpose, followed by critical behavioral warning about the API key. Every word earns its place with no redundancy or fluff.

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

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

For a registration tool with no output schema, the description adequately covers what the tool does and the key behavioral constraint. However, it doesn't describe the return format beyond mentioning an API key, nor does it explain potential errors or prerequisites. Given the annotations cover safety, it's mostly complete but could benefit from more output details.

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 schema already documents both parameters thoroughly. The description doesn't add meaning beyond what's in the schema (e.g., it doesn't explain the relationship between name uniqueness and the vestauth alternative). Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the specific action ('Register as an agent'), the resource ('AgentDeals'), and the purpose ('enable referral attribution and commission tracking'). It distinguishes this from sibling tools like 'check_balance' or 'submit_referral_code' by focusing on initial setup rather than ongoing operations.

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 this should be used for initial registration to get API access, but it doesn't explicitly state when not to use it (e.g., after already registered) or name alternatives like using existing authentication methods. The context is clear but lacks explicit exclusions.

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

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

The description adds valuable behavioral context beyond the annotations: it specifies that the full balance is withdrawn (no partial payouts), mentions the $10 minimum threshold, and outlines prerequisites (registered address). While annotations indicate it's not read-only and not destructive, the description provides operational constraints that aren't captured in structured fields.

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

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

The description is efficiently structured in three sentences that each serve a distinct purpose: stating the core function, listing prerequisites, and explaining withdrawal behavior. There's no wasted language, and the most critical information appears first.

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 financial transaction tool with no output schema, the description provides good context about prerequisites, constraints, and operational behavior. It could be more complete by mentioning response format or confirmation details, but it covers the essential transactional aspects well given 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?

With 100% schema description coverage, the input schema already fully documents the single 'api_key' parameter. The description doesn't add any additional parameter-specific information beyond what's in the schema, so it meets the baseline expectation without providing extra value.

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

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

The description clearly states the specific action ('Request a payout'), the resource ('confirmed referral credits'), and the method ('via x402 stablecoin transfer'). It distinguishes this from sibling tools like 'check_balance' by focusing on the withdrawal process rather than balance inquiry.

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

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

The description explicitly states when to use this tool: when you want to withdraw confirmed referral credits via stablecoin transfer. It also provides clear prerequisites (registered x402 address, confirmed balance >= $10) and exclusions (no partial payouts in Phase 2), which helps differentiate it from alternatives like simply checking balances.

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=true and destructiveHint=false. Description reinforces this safety profile and adds valuable behavioral context: 'Returns verified deal details including specific limits, eligibility requirements, and verification dates.' This disclosure of return content is crucial given the absence of an output schema, helping the agent understand data freshness and granularity before invoking.

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

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

Four well-structured sentences, each earning its place: (1) capability definition, (2) usage context, (3) output specification, (4) example trigger phrases. No redundancy or tautology. Front-loaded with the core action 'Find' and logically sequenced.

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 10 parameters with complete schema coverage and no output schema, the description adequately compensates by describing return values (deal details, limits, verification dates) and providing rich example queries. Missing only pagination behavior details beyond parameter existence, which is acceptable for a search tool of this 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 description coverage is 100%, with all 10 parameters fully documented (stability enum values explained, eligibility types listed, etc.). Description implies parameter usage through examples (vendor names like 'Supabase') but does not add semantic meaning beyond the schema's comprehensive definitions. Baseline 3 is appropriate as the schema carries the full burden.

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 uses specific verb 'Find' with clear resource 'deals/free tiers' and lists concrete domains (cloud infrastructure, databases, hosting, CI/CD, etc.). The scope is well-defined and distinguishes from siblings (e.g., compare_vendors implies comparison of known entities, while this focuses on discovery/search across a deal database).

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 when-to-use guidance: 'Use this when evaluating technology options, looking for free alternatives, or checking if a service has a free tier.' Includes specific example user queries ('Does Supabase have a free tier?', 'What's cheaper than Vercel?') that clearly signal intent. Lacks explicit 'when-not-to-use' or direct sibling differentiation, but examples effectively convey appropriate 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?

The description adds valuable behavioral context beyond annotations: it specifies authentication requirements ('Requires authentication via API key'), describes the review process ('pending review' vs 'auto-approved'), and implies a mutation (submission). Annotations (readOnlyHint=false, destructiveHint=false) already indicate it's a non-destructive write, so the description complements rather than contradicts them, earning a high score for added clarity.

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

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

The description is front-loaded with the core purpose, followed by essential prerequisites and behavioral details. Every sentence adds value—no fluff or repetition—making it highly efficient and well-structured 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?

For a mutation tool with no output schema, the description is largely complete: it covers purpose, authentication, and behavioral outcomes. However, it lacks details on error cases or response format, which could enhance completeness. Given the good annotations and schema coverage, it's still strong but not perfect.

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 input schema fully documents all parameters. The description does not add specific parameter semantics beyond what's in the schema, but it implicitly references 'vendor' and 'code' in context. This meets the baseline of 3, as the schema handles the heavy lifting.

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

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

The description clearly states the specific action ('Submit your own referral code') and resource ('for a vendor in the AgentDeals index'), distinguishing it from sibling tools like 'get_referral_code' or 'my_referral_codes' which retrieve rather than submit codes. It precisely defines the tool's function without ambiguity.

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

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

The description explicitly states when to use this tool ('Submit your own referral code') and provides clear prerequisites ('Requires authentication via API key (from register_agent)'). It also distinguishes usage based on agent status ('New agents' codes are pending review; verified/trusted agents' codes are auto-approved'), offering context for expected outcomes.

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 establish read-only, non-destructive safety. The description adds domain context about what change types are monitored (free tier removals, limit cuts), but does not disclose technical operational traits like data freshness, caching behavior, rate limits, or authentication requirements that would aid invocation planning.

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 tightly constructed sentences with zero redundancy: sentence 1 defines capability with examples, sentence 2 states use cases, sentence 3 provides explicit trigger phrases. Every sentence earns its place and facilitates rapid agent 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?

For an 8-parameter tool with 100% schema coverage and no output schema, the description adequately covers primary use cases and filtering intent (via the change type examples). Minor gap: could explicitly mention vendor/category filtering capabilities to fully prepare the agent for the available granularity, though this is discoverable in the schema.

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

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

Schema description coverage is 100%, so the baseline is 3. The description implicitly references the 'since' parameter via 'recent' and hints at 'change_type' values (free tiers removed, limits cut), but does not explicitly clarify parameter semantics, defaults, or interactions beyond what the schema already provides.

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 specific verbs ('Track') and resources ('pricing changes across developer tools') and enumerates specific change types tracked (free tiers removed, limits cut, improvements). It clearly distinguishes from siblings by focusing on temporal changes and monitoring rather than comparison (compare_vendors), planning (plan_stack), or deal discovery (search_deals).

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 positive triggers ('Use this to stay current...', 'Call this tool when a user asks...') with specific example queries. Lacks explicit negative guidance (when not to use) or direct sibling comparisons, but the example user queries clearly demarcate appropriate usage contexts.

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