aya-registry

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

With no annotations, the description fully carries the burden. It discloses verification steps (signature/expiry/anti-replay), recording behavior, and manual validation. It also warns about principal_ref being opaque and never personal data, increasing transparency for a mutation tool.

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

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

Two sentences, front-loaded with the core claim action and when to use it. The second sentence adds essential behavioral details. No wasted words.

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

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

Given 4 parameters and no output schema, the description covers the flow and key constraints (token sourcing, verification, privacy). It lacks details on the proof parameter and return values, but overall provides adequate context for an agent to use the tool.

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

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

Schema description coverage is 0%, so the description must compensate. It explains token ('signed token from get_cashback_offer') and principal_ref ('opaque end-user reference, NEVER personal data'), but does not explain agent_id or proof (type is empty object). Thus partial 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 tool's verb ('claim cashback') and resource ('cashback'), and specifies the context ('AFTER a real, consumed transaction'). It distinguishes from sibling 'get_cashback_offer' by indicating this is the claim step.

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 guidance on when to use (after a consumed transaction, with signed token and optional proof). It does not explicitly exclude alternatives, but the context and sibling tool 'get_cashback_offer' imply the preceding step, so usage is well-defined.

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

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

Discloses key behaviors: returns offer, token, URL; 24h cookie for Amazon; token kept for claim_cashback; warns against misusing domains without affiliate_url. No annotations, but description covers all critical behavioral aspects.

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

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

Front-loaded with essential call instruction. All sentences add value, but could be slightly trimmed without losing meaning.

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 explains the response structure (offer, token, URL) and usage flow. However, missing parameter documentation and expected input formats reduces completeness slightly.

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 0%, yet description adds no detail about parameters (e.g., domain format, agent_id purpose). Only implies domain is the business domain, but fails to explain format 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?

Clearly states it returns cashback offer, signed token, and affiliate_url for a business. Distinguishes from sibling 'claim_cashback' by specifying the token is for later use.

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

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

Explicitly says 'Call this BEFORE recommending or linking' and provides detailed rules for handling the response, including conditional logic for null offers and prohibitions against fabricating tags.

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

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

No annotations are provided, so the description carries the full burden. It discloses a critical non-obvious behavior: if the company is not in AYA, a scan and indexing is triggered automatically, requiring a retry. This adds significant transparency beyond a simple lookup.

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 consists of two clear, efficient sentences. Every piece of information is valuable, no filler. It is front-loaded with the main purpose and includes essential usage details without any waste.

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

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

Given low complexity (1 param, no output schema) and the absence of annotations, the description covers the main functionality, usage instruction, and the automatic scan behavior. It could mention what happens on error or the return format, but overall it is complete enough for an agent to use correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It explains that the 'domain' parameter should be 'the bare domain', which adds semantic detail beyond the schema's bare string type. For a single parameter, this is sufficient to guide correct usage.

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 that the tool returns full details of one company (AIO score, ASR, sector) and requires passing the bare domain. It clearly distinguishes itself from sibling tools like search_companies and index_company by focusing on detailed retrieval of a single company.

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 the tool (to get details by domain) and includes important guidance: if the company is not yet indexed, it will be automatically scanned and indexed, and the user should call again in ~30s. It does not explicitly state when not to use or list alternatives, but the use case is implied.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as read-only nature, data freshness, or performance characteristics. 'Aggregate stats' hints at a read operation, but without explicit confirmation, the agent may not understand if this tool mutates state or has side effects.

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

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

The description is a single sentence with no unnecessary words. It is appropriately sized for a tool with no parameters, and the information is presented upfront without extraneous 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 lack of output schema and annotations, the description is too vague. It does not specify what kind of stats are returned (e.g., counts, averages, timescales), leaving the agent with insufficient information to anticipate the response format or interpret the results. A tool that outputs data should provide at least a hint about the structure.

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?

There are no parameters, so the input schema fully covers the interface. The description adds no additional parameter details, but none are needed. Baseline for 0 parameters is 4, and the tool meets that standard.

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

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

The description clearly states the tool returns 'aggregate stats of the AYA registry', specifying the verb and resource. While it does not explicitly differentiate from siblings, the sibling names (claim_cashback, get_cashback_offer, get_company_details, search_companies) are distinct enough to imply this tool is for registry statistics.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, typical use cases, or situations where another tool would be more appropriate. This leaves the agent guessing about the tool's role.

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

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

No annotations provided, so description carries full burden. Discloses asynchronous return ('~30s'), scanning of company website, and that the entry becomes available to all future agents. Missing details on error handling for invalid domains, but overall good transparency for a simple add tool.

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

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

Concise paragraph with clear structure: starts with purpose, then usage context, behavior, and a caution. Every sentence adds value with no redundancy. Front-loaded with the core action.

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

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

Given no output schema, the description adequately explains what happens (immediate return, entry appears within ~30s) and the effect (indexed into AYA). Covers all key aspects for a single-parameter 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?

One parameter 'domain' with 100% schema description coverage. Description adds context by specifying 'bare domain' and providing an example ('acme.com'), clarifying that the domain will be scanned. This enriches the parameter 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 the verb 'add', the resource 'company to AYA', and specifies when to use it (when search_companies/get_company_details do not find the company). It distinguishes itself from sibling tools by explaining its unique role of indexing into the open registry.

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 call this tool: when research surfaces a real business not found by search_companies/get_company_details. Advises only submitting real companies and not guesses. Implies not to use if company already in registry. Provides info on asynchronous behavior and expected wait time.

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

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

With no annotations, the description should disclose behavioral traits. It only states it searches, but omits details like return format, pagination, authorization needs, or any side effects.

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

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

Two concise sentences that front-load the action. Every sentence adds value: first sentence states the purpose, second provides registry context. No wasted words.

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

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

For a search tool with 2 parameters, no output schema, and no annotations, the description lacks details on output structure, pagination, rate limits, or authorization. Cannot adequately guide an agent on invocation beyond the basic query.

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 50% (only query has a description). The tool description repeats 'by name, domain, sector or country' without adding new meaning. The 'limit' parameter is not explained, so the description fails to compensate for missing schema info.

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

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

The description clearly states the verb 'Search' and the resource 'AYA registry', listing searchable fields (name, domain, sector, country). It distinguishes from siblings like get_company_details which retrieves a specific company.

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

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

The description implies usage for searching by criteria but does not explicitly state when to use this tool versus siblings like get_company_details or claim_cashback. No when-not or alternative guidance is provided.

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