DAP Bellwether

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

The description provides highly valuable operational data that is not in the annotations, including the tiered pricing structure, call limits (50 calls), and associated crypto transaction details (USDC on Base).

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

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

The description is extremely concise, efficiently combining the tool's core function with critical operational metadata (cost/rate limits) in a well-structured paragraph.

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 its low complexity (1 parameter) and the presence of annotations, the definition is complete, covering the precise use case, limitations, and external operational constraints.

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?

While the schema is highly descriptive, the description reinforces the semantic meaning of the ID—that it is a specific 'record id' used to retrieve historical amendments rather than just a random identifier. This adds useful intent to the parameter 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 clearly specifies the operation (get a record) and its function (review amendments and changes), providing context that distinguishes it from broader search or listing tools among the siblings.

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

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

It provides a direct usage guideline: 'Use when you have a record id,' implicitly directing users away from the sibling tools that require broader search criteria or list generation.

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 openWorldHint=false, so safety is covered; the description adds the cost trait ('Always free') and the completeness of the result set ('every feed'), which are useful behavioral facts beyond the 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 tight sentences with the usage trigger front-loaded and no filler. Slightly compressed phrasing ('how fresh each is', 'Always free' tacked on the end) keeps it just below ideal polish.

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

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

With no parameters, no output schema, and annotations covering the safety profile, the description still explains what the caller gets back (feeds plus last-collected time) and the caveat about coverage gaps, which is everything needed to call it 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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate at the input level.

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?

States a specific verb and resource (lists regulators/feeds), the payload (last collected time for every feed), and implicitly distinguishes itself from the sibling change-retrieval tools by framing itself as coverage metadata rather than publications.

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?

Gives an explicit when-to-use trigger: before interpreting an empty result set as no publications. It does not name a sibling alternative or a when-not-to-use case, which keeps it short of a 5.

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 openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral facts: a 50-call-per-caller-per-UTC-day free quota, then $0.01 USDC on Base via x402, which an agent needs before calling in bulk. It does not describe pagination behavior or what a returned publication record contains.

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, zero waste: the first covers when-to-use and scope, the second covers cross-cutting regulator coverage, ordering, and cost. Front-loaded with the selection condition, with pricing placed last where it belongs.

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 parameterless-required read-only list tool with full schema coverage and clear annotations, almost everything needed to call it is present, including cost and ordering. The remaining gap is that it never indicates what fields a returned publication carries, which matters somewhat since no output schema exists.

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 each parameter documented including defaults and bounds, so the baseline is 3. The description only echoes the jurisdiction filter ('optionally for one jurisdiction') and adds no interpretation of days or limit 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?

States a specific verb and resource ('Lists the latest publications across every covered regulator'), plus ordering ('newest first') and an optional filter. The clause 'what is new from financial regulators rather than a specific topic' implicitly separates it from the topic-search sibling, so an agent can route correctly without opening a schema.

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 opening 'Use when you need what is new... rather than a specific topic' gives a clear trigger condition and an implicit exclusion. It stops short of naming search_regulatory_changes or get_regulatory_change as the alternatives, which would make routing unambiguous, so it is strong but not maximal.

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 openWorldHint=false, so safety is covered. The description adds value beyond that with the sort order, the fields returned for each record, and an explicit cost model (50 free calls per caller per UTC day, then $0.01 USDC on Base via x402), which is exactly the kind of operational context an agent must know before calling.

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 the use condition, then result shape, then pricing. Every sentence carries distinct operational information and there is no filler or repetition of the name.

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

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

With no output schema, the description does its duty by stating that records come back newest first with a link and an id. Coverage, filters, and limits are fully handled by the schema, and cost is disclosed, leaving only minor gaps such as total-result or pagination 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% and each parameter already documents its matching and date-normalization semantics in detail. The description only echoes 'on a topic or in a date range', adding no syntax, default, or interaction detail beyond the schema; baseline 3 applies.

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 names a specific action and resource: searching publications from financial regulators in Canada, the US, the UK and the EU by topic or date range. It is clearly a search/list tool, but it never names or contrasts the siblings get_regulatory_change and recent_regulatory_changes, so an agent must infer the boundary itself.

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?

"Use when you need what financial regulators ... have published on a topic or in a date range" gives a concrete triggering condition, including the two primary filter modes. There are no when-not conditions or named alternatives for the very similar recent_regulatory_changes and get_regulatory_change tools.

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